Document understanding using data mining and machine learning techniques

With the explosive growth of the volume and complexity of document data (e.g., news, blogs, web pages), it has become a necessity to semantically understand documents and deliver meaningful information to users. Areas dealing with these problems are crossing data mining, information retrieval, and machine learning. For example, document clustering and summarization are two fundamental techniques for understanding document data and have attracted much attention in recent years. Given a collection of documents, document clustering aims to partition them into different groups to provide efficient document browsing and navigation mechanisms. One unrevealed area in document clustering is that how to generate meaningful interpretation for the each document cluster resulted from the clustering process. Document summarization is another effective technique for document understanding, which generates a summary by selecting sentences that deliver the major or topic-relevant information in the original documents. How to improve the automatic summarization performance and apply it to newly emerging problems are two valuable research directions. To assist people to capture the semantics of documents effectively and efficiently, the dissertation focuses on developing effective data mining and machine learning algorithms and systems for (1) integrating document clustering and summarization to obtain meaningful document clusters with summarized interpretation, (2) improving document summarization performance and building document understanding systems to solve real-world applications, and (3) summarizing the differences and evolution of multiple document sources.

Mitigating congestion by integrating time forecasting and realtime information aggregation in cellular networks

An iterative travel time forecasting scheme, named the Advanced Multilane Prediction based Real-time Fastest Path (AMPRFP) algorithm, is presented in this dissertation. This scheme is derived from the conventional kernel estimator based prediction model by the association of real-time nonlinear impacts that caused by neighboring arcs’ traffic patterns with the historical traffic behaviors. The AMPRFP algorithm is evaluated by prediction of the travel time of congested arcs in the urban area of Jacksonville City. Experiment results illustrate that the proposed scheme is able to significantly reduce both the relative mean error (RME) and the root-mean-squared error (RMSE) of the predicted travel time. To obtain high quality real-time traffic information, which is essential to the performance of the AMPRFP algorithm, a data clean scheme enhanced empirical learning (DCSEEL) algorithm is also introduced. This novel method investigates the correlation between distance and direction in the geometrical map, which is not considered in existing fingerprint localization methods. Specifically, empirical learning methods are applied to minimize the error that exists in the estimated distance. A direction filter is developed to clean joints that have negative influence to the localization accuracy. Synthetic experiments in urban, suburban and rural environments are designed to evaluate the performance of DCSEEL algorithm in determining the cellular probe’s position. The results show that the cellular probe’s localization accuracy can be notably improved by the DCSEEL algorithm. Additionally, a new fast correlation technique for overcoming the time efficiency problem of the existing correlation algorithm based floating car data (FCD) technique is developed. The matching process is transformed into a 1-dimensional (1-D) curve matching problem and the Fast Normalized Cross-Correlation (FNCC) algorithm is introduced to supersede the Pearson product Moment Correlation Co-efficient (PMCC) algorithm in order to achieve the real-time requirement of the FCD method. The fast correlation technique shows a significant improvement in reducing the computational cost without affecting the accuracy of the matching process.

Integrating Technology in a Statistics Course for a Special Program at Florida International University

A special undergraduate program for selected biology majors was recently inaugurated at Florida International University. The curriculum emphasizes science, mathematics, and statistics. A statistics course was implemented for this program integrating PowerPoint, statistical software (SPSS), and data from biological/biomedical studies. This didactic experience is discussed here.

Anomaly detection from time-changing environmental sensor data streams

This thesis stems from the project with real-time environmental monitoring company EMSAT Corporation. They were looking for methods to automatically ag spikes and other anomalies in their environmental sensor data streams. The problem presents several challenges: near real-time anomaly detection, absence of labeled data and time-changing data streams. Here, we address this problem using both a statistical parametric approach as well as a non-parametric approach like Kernel Density Estimation (KDE). The main contribution of this thesis is extending the KDE to work more effectively for evolving data streams, particularly in presence of concept drift. To address that, we have developed a framework for integrating Adaptive Windowing (ADWIN) change detection algorithm with KDE. We have tested this approach on several real world data sets and received positive feedback from our industry collaborator. Some results appearing in this thesis have been presented at ECML PKDD 2015 Doctoral Consortium.

Electronic health records: essential tools in integrating substance abuse treatment with primary care.

While substance use problems are considered to be common in medical settings, they are not systematically assessed and diagnosed for treatment management. Research data suggest that the majority of individuals with a substance use disorder either do not use treatment or delay treatment-seeking for over a decade. The separation of substance abuse services from mainstream medical care and a lack of preventive services for substance abuse in primary care can contribute to under-detection of substance use problems. When fully enacted in 2014, the Patient Protection and Affordable Care Act 2010 will address these barriers by supporting preventive services for substance abuse (screening, counseling) and integration of substance abuse care with primary care. One key factor that can help to achieve this goal is to incorporate the standardized screeners or common data elements for substance use and related disorders into the electronic health records (EHR) system in the health care setting. Incentives for care providers to adopt an EHR system for meaningful use are part of the Health Information Technology for Economic and Clinical Health Act 2009. This commentary focuses on recent evidence about routine screening and intervention for alcohol/drug use and related disorders in primary care. Federal efforts in developing common data elements for use as screeners for substance use and related disorders are described. A pressing need for empirical data on screening, brief intervention, and referral to treatment (SBIRT) for drug-related disorders to inform SBIRT and related EHR efforts is highlighted.

Childhood obesity treatment: integrating mobile health technology into a paediatric obesity service

Background: The management of childhood obesity is challenging. Aims: Thesis, i) reviews the evidence for lifestyle treatment of obesity, ii) explores cardiometabolic burden in childhood obesity, iii) explores whether changes in body composition predicts change in insulin sensitivity (IS), iv) develops and evaluates a lifestyle obesity intervention; v) develops a mobile health application for obesity treatment and vi) tests the application in a clinical trial. Methods: In Study 1, systematic reviews and meta-analyses of the 12‐month effects of lifestyle and mHealth interventions were conducted. In Study 2, the prevalence of cardiometabolic burden was estimated in a consecutive series of 267 children. In Study 3, body composition was estimated with bioelectrical impedance analysis (BIA) and dual x-ray absorptiometry (DXA) and linear regression analyses were used to estimate the extent to which each methods predicted change in IS. Study 4 describes the development of the Temple Street W82GO Healthy Lifestyle intervention for clinical obesity in children and a controlled study of treatment effect in 276 children is reported. Study 5 describes the development and testing of the Reactivate Mobile Obesity Application. Study 6 outlines the development and preliminary report from a clinical effectiveness trial of Reactivate. Results: In Study 1, meta--‐analyses BMI SDS changed by -0.16 (-0.24,‐0.07, p<0.01) and -0.03 (-0.13, 0.06, p=0.48). In study 2, cardiometabolic comorbidities were common (e.g. hypertension in 49%) and prevalence increased as obesity level increased. In Study 3, BC changes significantly predicted changes in IS. In Study 4, BMI SDS was significantly reduced in W82GO compared to controls (p<0.001). In Study 5, the Reactivate application had good usability indices and preliminary 6‐month process report data from Study 6, revealed a promising effect for Reactivate. Conclusions: W82GO and Reactivate are promising forms of treatment.

Building a 'Repository of Science': the importance of integrating Biobanks within molecular pathology programmes

Repositories containing high quality human biospecimens linked with robust and relevant clinical and pathological information are required for the discovery and validation of biomarkers for disease diagnosis, progression and response to treatment. Current molecular based discovery projects using either low or high throughput technologies rely heavily on ready access to such sample collections. It is imperative that modern biobanks align with molecular diagnostic pathology practices not only to provide the type of samples needed for discovery projects but also to ensure requirements for ongoing sample collections and the future needs of researchers are adequately addressed. Biobanks within comprehensive molecular pathology programmes are perfectly positioned to offer more than just tumour derived biospecimens; for example, they have the ability to facilitate researchers gaining access to sample metadata such as digitised scans of tissue samples annotated prior to macrodissection for molecular diagnostics or pseudoanonymised clinical outcome data or research results retrieved from other users utilising the same or overlapping cohorts of samples. Furthermore, biobanks can work with molecular diagnostic laboratories to develop standardized methodologies for the acquisition and storage of samples required for new approaches to research such as ‘liquid biopsies’ which will ultimately feed into the test validations required in large prospective clinical studies in order to implement liquid biopsy approaches for routine clinical practice. We draw on our experience in Northern Ireland to discuss how this harmonised approach of biobanks working synergistically with molecular pathology programmes is key for the future success of precision medicine.

Decisions, decisions everywhere (in the open data era).

Abstract: Decision support systems have been widely used for years in companies to gain insights from internal data, thus making successful decisions. Lately, thanks to the increasing availability of open data, these systems are also integrating open data to enrich decision making process with external data. On the other hand, within an open-data scenario, decision support systems can be also useful to decide which data should be opened, not only by considering technical or legal constraints, but other requirements, such as "reusing potential" of data. In this talk, we focus on both issues: (i) open data for decision making, and (ii) decision making for opening data. We will first briefly comment some research problems regarding using open data for decision making. Then, we will give an outline of a novel decision-making approach (based on how open data is being actually used in open-source projects hosted in Github) for supporting open data publication. Bio of the speaker: Jose-Norberto Mazón holds a PhD from the University of Alicante (Spain). He is head of the "Cátedra Telefónica" on Big Data and coordinator of the Computing degree at the University of Alicante. He is also member of the WaKe research group at the University of Alicante. His research work focuses on open data management, data integration and business intelligence within "big data" scenarios, and their application to the tourism domain (smart tourism destinations). He has published his research in international journals, such as Decision Support Systems, Information Sciences, Data & Knowledge Engineering or ACM Transaction on the Web. Finally, he is involved in the open data project in the University of Alicante, including its open data portal at http://datos.ua.es

Integrating functional connectivity and climate change in the design of protected area networks

Le rapide déclin actuel de la biodiversité est inquiétant et les activités humaines en sont la cause directe. De nombreuses aires protégées ont été mises en place pour contrer cette perte de biodiversité. Afin de maximiser leur efficacité, l’amélioration de la connectivité fonctionnelle entre elles est requise. Les changements climatiques perturbent actuellement les conditions environnementales de façon globale. C’est une menace pour la biodiversité qui n’a pas souvent été intégrée lors de la mise en place des aires protégées, jusqu’à récemment. Le mouvement des espèces, et donc la connectivité fonctionnelle du paysage, est impacté par les changements climatiques et des études ont montré qu’améliorer la connectivité fonctionnelle entre les aires protégées aiderait les espèces à faire face aux impacts des changements climatiques. Ma thèse présente une méthode pour concevoir des réseaux d’aires protégées tout en tenant compte des changements climatiques et de la connectivité fonctionnelle. Mon aire d’étude est la région de la Gaspésie au Québec (Canada). La population en voie de disparition de caribou de la Gaspésie-Atlantique (Rangifer tarandus caribou) a été utilisée comme espèce focale pour définir la connectivité fonctionnelle. Cette petite population subit un déclin continu dû à la prédation et la modification de son habitat, et les changements climatiques pourraient devenir une menace supplémentaire. J’ai d’abord construit un modèle individu-centré spatialement explicite pour expliquer et simuler le mouvement du caribou. J’ai utilisé les données VHF éparses de la population de caribou et une stratégie de modélisation patron-orienté pour paramétrer et sélectionner la meilleure hypothèse de mouvement. Mon meilleur modèle a reproduit la plupart des patrons de mouvement définis avec les données observées. Ce modèle fournit une meilleure compréhension des moteurs du mouvement du caribou de la Gaspésie-Atlantique, ainsi qu’une estimation spatiale de son utilisation du paysage dans la région. J’ai conclu que les données éparses étaient suffisantes pour ajuster un modèle individu-centré lorsqu’utilisé avec une modélisation patron-orienté. Ensuite, j’ai estimé l’impact des changements climatiques et de différentes actions de conservation sur le potentiel de mouvement du caribou. J’ai utilisé le modèle individu-centré pour simuler le mouvement du caribou dans des paysages hypothétiques représentant différents scénarios de changements climatiques et d’actions de conservation. Les actions de conservation représentaient la mise en place de nouvelles aires protégées en Gaspésie, comme définies par le scénario proposé par le gouvernement du Québec, ainsi que la restauration de routes secondaires à l’intérieur des aires protégées. Les impacts des changements climatiques sur la végétation, comme définis dans mes scénarios, ont réduit le potentiel de mouvement du caribou. La restauration des routes était capable d’atténuer ces effets négatifs, contrairement à la mise en place des nouvelles aires protégées. Enfin, j’ai présenté une méthode pour concevoir des réseaux d’aires protégées efficaces et j’ai proposé des nouvelles aires protégées à mettre en place en Gaspésie afin de protéger la biodiversité sur le long terme. J’ai créé de nombreux scénarios de réseaux d’aires protégées en étendant le réseau actuel pour protéger 12% du territoire. J’ai calculé la représentativité écologique et deux mesures de connectivité fonctionnelle sur le long terme pour chaque réseau. Les mesures de connectivité fonctionnelle représentaient l’accès général aux aires protégées pour le caribou de la Gaspésie-Atlantique ainsi que son potentiel de mouvement à l’intérieur. J’ai utilisé les estimations de potentiel de mouvement pour la période de temps actuelle ainsi que pour le futur sous différents scénarios de changements climatiques pour représenter la connectivité fonctionnelle sur le long terme. Le réseau d’aires protégées que j’ai proposé était le scénario qui maximisait le compromis entre les trois caractéristiques de réseau calculées. Dans cette thèse, j’ai expliqué et prédit le mouvement du caribou de la Gaspésie-Atlantique sous différentes conditions environnementales, notamment des paysages impactés par les changements climatiques. Ces résultats m’ont aidée à définir un réseau d’aires protégées à mettre en place en Gaspésie pour protéger le caribou au cours du temps. Je crois que cette thèse apporte de nouvelles connaissances sur le comportement de mouvement du caribou de la Gaspésie-Atlantique, ainsi que sur les actions de conservation qui peuvent être prises en Gaspésie afin d’améliorer la protection du caribou et de celle d’autres espèces. Je crois que la méthode présentée peut être applicable à d’autres écosystèmes aux caractéristiques et besoins similaires.

The challenges of integrating biodiversity and ecosystem services monitoring and evaluation at a landscape-scale wetland restoration project in the UK

There is an increasing emphasis on the restoration of ecosystem services as well as of biodiversity, especially where restoration projects are planned at a landscape scale. This increase in the diversity of restoration aims has a number of conceptual and practical implications for the way that restoration projects are monitored and evaluated. Landscape-scale projects require monitoring of not only ecosystem services and biodiversity but also of ecosystem processes since these can underpin both. Using the experiences gained at a landscape-scale wetland restoration project in the UK, we discuss a number of issues that need to be considered, including the choice of metrics for monitoring ecosystem services and the difficulties of assessing the interactions between ecosystem processes, biodiversity, and ecosystem services. Particular challenges that we identify, using two pilot data sets, include the decoupling of monetary metrics used for monitoring ecosystem services from biophysical change on the ground and the wide range of factors external to a project that influence the monitoring results. We highlight the fact that the wide range of metrics necessary to evaluate the ecosystem service, ecosystem process, and biodiversity outcomes of landscape-scale projects presents a number of practical challenges, including the need for high levels of varied expertise, high costs, incommensurate monitoring outputs, and the need for careful management of monitoring results, especially where they may be used in making decisions about the relative importance of project aims.

Integrating Mindfulness into Positive Psychology: a Randomised Controlled Trial of an Online Positive Mindfulness Program

The purpose of the present study was to test the efficacy of an 8-week online intervention-based Positive Mindfulness Program (PMP) that integrated mindfulness with a series of positive psychology variables, with a view to improving wellbeing scores measured in these variables. The positive mindfulness cycle, based on positive intentions and savouring, provides the theoretical foundation for the PMP. The study was based on a randomised wait-list controlled trial; and 168 participants (128 females, mean age = 40.82) completed the intervention which included daily videos, meditations, and activities. The variables tested included wellbeing measures, such as gratitude, self-compassion, self-efficacy, meaning, and autonomy. Pre- and post- intervention data, including one month after the end of the intervention, were collected from both experimental and control groups. The post-test measurements of the experimental participants showed a significant improvement in all the dependent variables compared with the pre-test ones and were also significantly higher than those of the control group. One month after the intervention, the experimental group participants retained their improvement in 10 out of the 11 measurements. These positive results indicate that PMP may be effective in enhancing wellbeing and other positive variables in adult, non-clinical populations.

The challenges of integrating the discussion of controversial issues in initial teacher training

In the framework of the Bologna process, and with regard to pre-service teacher education, it is necessary to model student-centred learning experiences in order to promote the required competences for future professional practice and critical participation in society. Despite the potential of discussion in promoting several competences, this methodology does not always integrate the teaching practices. This case study sought to: a) understand the experiences and views of future teachers from a School of Education on the use of discussion in their past education; and b) investigate the impact of an educational experience centred on discussion. Data were collected through narratives, questionnaires, interviews and participant observation. The learning situations experienced through this study contributed to the development of citizens more aware of their role in society and allowed the promotion of skills indispensable for an Elementary Education teacher.

The challenges of integrating the discussion of controversial issues in initial teacher training

In the framework of the Bologna process, and with regard to pre-service teacher education, it is necessary to model student-centred learning experiences in order to promote the required competences for future professional practice and critical participation in society. Despite the potential of discussion in promoting several competences, this methodology does not always integrate the teaching practices. This case study sought to: a) understand the experiences and views of future teachers from a School of Education on the use of discussion in their past education; and b) investigate the impact of an educational experience centred on discussion. Data were collected through narratives, questionnaires, interviews and participant observation. The learning situations experienced through this study contributed to the development of citizens more aware of their role in society and allowed the promotion of skills indispensable for an Elementary Education teacher.

Chronic contamination assessment integrating biomarkers' responses in transplanted mussels-A seasonal monitoring

This study aimed to provide the first biomonitoring integrating biomarkers and bioaccumulation data in São Paulo coast, Brazil and, for this purpose, a battery of biomarkers of defense mechanisms was analyzed and linked to contaminants' body burden in a weigh-of-evidence approach. The brown mussel Perna perna was selected to be transplanted from a farming area (Caraguatatuba) to four possibly polluted sites: Engenho D'Agua, DTCS (Dutos e Terminais do Centro-Oeste de São Paulo) oil terminal (Sao Sebastiao zone), Palmas Island, and Itaipu (It; Santos Bay zone). After 3 months of exposure in each season, mussels were recollected and the cytochrome P4501A (CYP1A)- and CYP3A-like activities, glutathione-S-transferase and antioxidants enzymes (catalase, glutathione peroxidase, and glutathione reductase) were analyzed in gills. The concentrations of polycyclic aromatic hydrocarbons, linear alkylbenzenes, and nonessential metals (Cr, Cd, Pb, and Hg) in whole tissue were also analyzed and data were linked to biomarkers' responses by multivariate analysis (principal component analysisfactor analysis). A representation of estimated factor scores was performed to confirm the factor descriptions and to characterize the studied stations. Biomarkers exhibited most significant alterations all year long in mussels transplanted to It, located at Santos Bay zone, where bioaccumulation of organic and inorganic compounds was detected. This integrated approach using transplanted mussels showed satisfactory results, pointing out differences between sites, seasons, and critical areas, which could be related to land-based contaminants' sources. The influence of natural factors and other contaminants (e.g., pharmaceuticals) on biomarkers' responses are also discussed. (C) 2010 Wiley Periodicals, Inc. Environ Toxicol, 2012.

DATA DRIVEN INTELLIGENT AGENT NETWORKS FOR ADAPTIVE MONITORING AND CONTROL

To analyze the characteristics and predict the dynamic behaviors of complex systems over time, comprehensive research to enable the development of systems that can intelligently adapt to the evolving conditions and infer new knowledge with algorithms that are not predesigned is crucially needed. This dissertation research studies the integration of the techniques and methodologies resulted from the fields of pattern recognition, intelligent agents, artificial immune systems, and distributed computing platforms, to create technologies that can more accurately describe and control the dynamics of real-world complex systems. The need for such technologies is emerging in manufacturing, transportation, hazard mitigation, weather and climate prediction, homeland security, and emergency response. Motivated by the ability of mobile agents to dynamically incorporate additional computational and control algorithms into executing applications, mobile agent technology is employed in this research for the adaptive sensing and monitoring in a wireless sensor network. Mobile agents are software components that can travel from one computing platform to another in a network and carry programs and data states that are needed for performing the assigned tasks. To support the generation, migration, communication, and management of mobile monitoring agents, an embeddable mobile agent system (Mobile-C) is integrated with sensor nodes. Mobile monitoring agents visit distributed sensor nodes, read real-time sensor data, and perform anomaly detection using the equipped pattern recognition algorithms. The optimal control of agents is achieved by mimicking the adaptive immune response and the application of multi-objective optimization algorithms. The mobile agent approach provides potential to reduce the communication load and energy consumption in monitoring networks. The major research work of this dissertation project includes: (1) studying effective feature extraction methods for time series measurement data; (2) investigating the impact of the feature extraction methods and dissimilarity measures on the performance of pattern recognition; (3) researching the effects of environmental factors on the performance of pattern recognition; (4) integrating an embeddable mobile agent system with wireless sensor nodes; (5) optimizing agent generation and distribution using artificial immune system concept and multi-objective algorithms; (6) applying mobile agent technology and pattern recognition algorithms for adaptive structural health monitoring and driving cycle pattern recognition; (7) developing a web-based monitoring network to enable the visualization and analysis of real-time sensor data remotely. Techniques and algorithms developed in this dissertation project will contribute to research advances in networked distributed systems operating under changing environments.