Jorge E. Camargo

BIGS: A framework for large-scale image processing and analysis over distributed and heterogeneous computing resources

This paper presents BIGS the Big Image Data Analysis Toolkit, a software framework for large scale image processing and analysis over heterogeneous computing resources, such as those available in clouds, grids, computer clusters or throughout scattered computer resources (desktops, labs) in an opportunistic manner. Through BIGS, eScience for image processing and analysis is conceived to exploit coarse grained parallelism based on data partitioning and parameter sweeps, avoiding the need of inter-process communication and, therefore, enabling loosely coupled computing nodes (BIGS workers). It adopts an uncommitted resource allocation model where (1) experimenters define their image processing pipelines in a simple configuration file, (2) a schedule of jobs is generated and (3) workers, as they become available, take over pending jobs as long as their dependency on other jobs is fulfilled. BIGS workers act autonomously, querying the job schedule to determine which one to take over. This removes the need for a central scheduling node, requiring only access by all workers to a shared information source. Furthermore, BIGS workers are encapsulated within different technologies to enable their agile deployment over the available computing resources. Currently they can be launched through the Amazon EC2 service over their cloud resources, through Java Web Start from any desktop computer and through regular scripting or SSH commands. This suits well different kinds of research environments, both when accessing dedicated computing clusters or clouds with committed computing capacity or when using opportunistic computing resources whose access is seldom or cannot be provisioned in advance. We also adopt a NoSQL storage model to ensure the scalability of the shared information sources required by all workers, including within BIGS support for HBase and Amazons DynamoDB service. Overall, BIGS now enables researchers to run large scale image processing pipelines in an easy, affordable and unplanned manner with the capability to take over computing resources as they become available at run time. This is shown in this paper by using BIGS in different experimental setups in the Amazon cloud and in an opportunistic manner, demonstrating its configurability, adaptability and scalability capabilities.

Monitoring of illicit pill distribution networks using an image collection exploration framework

This paper proposes a novel approach for the analysis of illicit tablets based on their visual characteristics. In particular, the paper concentrates on the problem of ecstasy pill seizure profiling and monitoring. The presented method extracts the visual information from pill images and builds a representation of it, i.e. it builds a pill profile based on the pill visual appearance. Different visual features are used to build different image similarity measures, which are the basis for a pill monitoring strategy based on both discriminative and clustering models. The discriminative model permits to infer whether two pills come from the same seizure, while the clustering models groups of pills that share similar visual characteristics. The resulting clustering structure allows to perform a visual identification of the relationships between different seizures. The proposed approach was evaluated using a data set of 621 Ecstasy pill pictures. The results demonstrate that this is a feasible and cost effective method for performing pill profiling and monitoring.

A Multi-class Kernel Alignment Method for Image Collection Summarization

This paper proposes a method for involving domain knowledge in the construction of summaries of large collections of images. This is accomplished by using a multi-class kernel alignment strategy in order to learn a kernel function that incorporates domain knowledge (class labels). The kernel function is the basis of a clustering algorithm that generates a subset, the summary, of the image collection. The method was tested with a subset of the Corel image collection using a summarization quality measure based on information theory. Experimental results show that it is possible to improve the quality of the summary when domain knowledge is involved.

A kernel-based framework for image collection exploration

While search engines have been a successful tool to search text information, image search systems still face challenges. The keyword-based query paradigm used to search in image collection systems, which has been successful in text retrieval, may not be useful in scenarios where the user does not have the precise way to express a visual query. Image collection exploration is a new paradigm where users interact with the image collection to discover useful and relevant pictures. This paper proposes a framework for the construction of an image collection exploration system based on kernel methods, which offers a mathematically strong basis to address each stage of an image collection exploration system: image representation, summarization, visualization and interaction. In particular, our approach emphasizes a semantic representation of images using kernel functions, which can be seamlessly harnessed across all system components. Experiments were conducted with real users to verify the effectiveness and efficiency of the proposed strategy.

Finding relationships between socio-technical aspects and personality traits by mining developer e-mails

Personality traits influence most, if not all, of the human activities, from those as natural as the way people walk, talk, dress and write to those most complex as the way they interact with others. Most importantly, personality influences the way people make decisions including, in the case of developers, the criteria they consider when selecting a software project they want to participate. Most of the works that study the influence of social, technical and human factors in software development projects have been focused on the impact of communications in software quality. For instance, on identifying predictors to detect files that may contain bugs before releasing an enhanced version of a software product. Only a few of these works focus on the analysis of personality traits of developers with commit permissions (committers) in Free/Libre and Open-Source Software projects and their relationship with the software artifacts they interact with. This paper presents an approach, based on the automatic recognition of personality traits from e-mails sent by committers in FLOSS projects, to uncover relationships between the social and technical aspects that occur during the software development process. Our experimental results suggest the existence of some relationships among personality traits projected by the committers through their e-mails and the social (communication) and technical activities they undertake. This work is a preliminary study aimed at supporting the setting up of efficient work teams in software development projects based on an appropriate mix of stakeholders taking into account their personality traits.

Multimodal latent topic analysis for image collection summarization

We present a new multimodal image collection summarization method.The summarization method is based on latent topic analysis.Textual and visual modalities are fused in the same latent space using convex non-negative matrix factorization.The obtained multimodal summarization involves textual and visual informations.We evaluate the proposed method using reconstruction error and summary diversity. This paper presents a multimodal latent topic analysis method for the construction of image collection summaries. The method automatically selects a set of prototypical images from a large set of retrieved images for a given query. We define an image collection summary as a subset of images from a collection, which is visually and semantically representative. To build such a summary we propose MICS (Multimodal Image Collection Summarization), a method that combines textual and visual modalities in a common latent space, which allows to find a subset of images from which the whole collection can be reconstructed. Experiments were conducted on two collections of tagged images demonstrating the ability of the approach to build summaries with representative visual and semantic contents. The method was evaluated using objective measures, reconstruction error and diversity of the summary, showing competitive results when compared to other summarization approaches.

Multimodal image collection summarization using non-negative matrix factorization

The huge amount of biomedical images that are produced every day require of suitable methods to access them in an efficient and effective way. Although there has been an important development in methods to search large information repositories, these methods have been mainly focused on text data, and less work has been devoted to non-text data such as images and video. This paper presents a new method that combines text and visual information in the same latent representation space in which images and text are jointly represented. We also investigate how to select the most representative elements of the collection to build an image collection summary. The proposed method was applied to a collection of histological images and the results where evaluated both qualitatively and quantitatively by an expert. The initial results show that the proposed method is able to build a meaningful summary that can be integrated in an image collection exploration system.

A survey on IEEE 802.11-based MANETs and DTNs for survivor communication in disaster scenarios

Ad hoc networks are spontaneous associations of wireless nodes that can operate without a previously built infrastructure. IEEE 802.11-based ad hoc networks, particularly, are the most common type of ad hoc networks since they can be deployed with ordinary devices such as laptops, tablets or smartphones. An application of ad hoc networks that is frequently mentioned in the literature is that of supporting communication between survivors or members of rescue teams in post-disaster scenarios. In these circumstances, ad hoc networks of mobile devices could be rapidly configured to communicate survivors and, in turn, could indirectly aid first responders to locate injured people. Among the different paradigms of ad hoc networks, numerous research efforts on post disaster communication have been focused on designing operating schemes for Mobile Ad Hoc NETworks (MANETs) and Delay Tolerant Networks (DTNs). Furthermore, some authors have proposed approaches that successfully integrate both paradigms. This paper is a comprehensive literature review on communication solutions based on MANETs and DTNs that employ the IEEE 802.11 standard. Specifically, this review studies proposals designed for post-disaster scenarios in which there is no communication infrastructure available and network nodes move following the mobility pattern of pedestrians.

Multimodal visualization based on latent topic analysis

Image collection visualization is an important component of exploration-based image retrieval systems. In this paper we address the problem of generating an image collection visualization in which images and text can be projected together. Given a collection of images with attached text annotations, our aim is to find a common representation for both information sources to model latent correlations among the collection. Using the proposed latent representation, an image collection visualization is built, in which both data modalities (images and text) can be projected simultaneously. The resulting collection visualization allows to identify the relationships between images and text terms, enabling a better understanding of the collection semantic structure. The resulting visualization scheme can be used as the core metaphor in an interactive image exploration system.

Predicting the Programming Language: Extracting Knowledge from Stack Overflow Posts

Stack Overflow (SO) is an important source of knowledge for developers. It provides authoritative advice as well as detailed technical information about different computer science and software engineering topics. The goal of this paper is to explore mechanisms to extract implicit knowledge, which is present in questions of SO. In particular, we want to extract information about programming languages and their relationships to such questions. The proposed approach builds a classifier model that predicts the programming language using the content (text and source code snippets) of a question. The proposed method produces word embeddings in which each term of the question is represented in a vectorial space in which it is possible to perform operations such as comparing words, sentences, and questions. The method was evaluated on a set of 18,000 questions related to 18 different programming languages. Results show that it is possible to extract interesting non-evident information from this highly unstructured data source.