Preface

The Semantic Web has come a long way since its inception in 2001, especially in terms of technical development and research progress. However, adoption by non- technical practitioners is still an ongoing process, and in some areas this process is just now starting. Emergency response is an area where reliability and timeliness of information and technologies is of essence. Therefore it is quite natural that more widespread adoption in this area has not been seen until now, when Semantic Web technologies are mature enough to support the high requirements of the application area. Nevertheless, to leverage the full potential of Semantic Web research results for this application area, there is need for an arena where practitioners and researchers can meet and exchange ideas and results. Our intention is for this workshop, and hopefully coming workshops in the same series, to be such an arena for discussion. The Extended Semantic Web Conference (ESWC - formerly the European Semantic Web conference) is one of the major research conferences in the Semantic Web field, whereas this is a suitable location for this workshop in order to discuss the application of Semantic Web technology to our specific area of applications. Hence, we chose to arrange our first SMILE workshop at ESWC 2013. However, this workshop does not focus solely on semantic technologies for emergency response, but rather Semantic Web technologies in combination with technologies and principles for what is sometimes called the "social web". Social media has already been used successfully in many cases, as a tool for supporting emergency response. The aim of this workshop is therefore to take this to the next level and answer questions like: "how can we make sense of, and furthermore make use of, all the data that is produced by different kinds of social media platforms in an emergency situation?" For the first edition of this workshop the chairs collected the following main topics of interest: • Semantic Annotation for understanding the content and context of social media streams. • Integration of Social Media with Linked Data. • Interactive Interfaces and visual analytics methodologies for managing multiple large-scale, dynamic, evolving datasets. • Stream reasoning and event detection. • Social Data Mining. • Collaborative tools and services for Citizens, Organisations, Communities. • Privacy, ethics, trustworthiness and legal issues in the Social Semantic Web. • Use case analysis, with specific interest for use cases that involve the application of Social Media and Linked Data methodologies in real-life scenarios. All of these, applied in the context of: • Crisis and Disaster Management • Emergency Response • Security and Citizen Journalism The workshop received 6 high-quality paper submissions and based on a thorough review process, thanks to our program committee, the decision was made to accept four of these papers for the workshop (67% acceptance rate). These four papers can be found later in this proceedings volume. Three out of four of these papers particularly discuss the integration and analysis of social media data, using Semantic Web technologies, e.g. for detecting complex events in social media streams, for visualizing and analysing sentiments with respect to certain topics in social media, or for detecting small-scale incidents entirely through the use of social media information. Finally, the fourth paper presents an architecture for using Semantic Web technologies in resource management during a disaster. Additionally, the workshop featured an invited keynote speech by Dr. Tomi Kauppinen from Aalto university. Dr. Kauppinen shared experiences from his work on applying Semantic Web technologies to application fields such as geoinformatics and scientific research, i.e. so-called Linked Science, but also recent ideas and applications in the emergency response field. His input was also highly valuable for the roadmapping discussion, which was held at the end of the workshop. A separate summary of the roadmapping session can be found at the end of these proceedings. Finally, we would like to thank our invited speaker Dr. Tomi Kauppinen, all our program committee members, as well as the workshop chair of ESWC2013, Johanna Völker (University of Mannheim), for helping us to make this first SMILE workshop a highly interesting and successful event!

Thermography-based virtual MPPT scheme for improving PV energy efficiency under partial shading conditions

This paper proposes a new thermography-based maximum power point tracking (MPPT) scheme to address photovoltaic (PV) partial shading faults. Solar power generation utilizes a large number of PV cells connected in series and in parallel in an array, and that are physically distributed across a large field. When a PV module is faulted or partial shading occurs, the PV system sees a nonuniform distribution of generated electrical power and thermal profile, and the generation of multiple maximum power points (MPPs). If left untreated, this reduces the overall power generation and severe faults may propagate, resulting in damage to the system. In this paper, a thermal camera is employed for fault detection and a new MPPT scheme is developed to alter the operating point to match an optimized MPP. Extensive data mining is conducted on the images from the thermal camera in order to locate global MPPs. Based on this, a virtual MPPT is set out to find the global MPP. This can reduce MPPT time and be used to calculate the MPP reference voltage. Finally, the proposed methodology is experimentally implemented and validated by tests on a 600-W PV array.

Actionable pattern analysis in computing and business intelligence systems

With advances in science and technology, computing and business intelligence (BI) systems are steadily becoming more complex with an increasing variety of heterogeneous software and hardware components. They are thus becoming progressively more difficult to monitor, manage and maintain. Traditional approaches to system management have largely relied on domain experts through a knowledge acquisition process that translates domain knowledge into operating rules and policies. It is widely acknowledged as a cumbersome, labor intensive, and error prone process, besides being difficult to keep up with the rapidly changing environments. In addition, many traditional business systems deliver primarily pre-defined historic metrics for a long-term strategic or mid-term tactical analysis, and lack the necessary flexibility to support evolving metrics or data collection for real-time operational analysis. There is thus a pressing need for automatic and efficient approaches to monitor and manage complex computing and BI systems. To realize the goal of autonomic management and enable self-management capabilities, we propose to mine system historical log data generated by computing and BI systems, and automatically extract actionable patterns from this data. This dissertation focuses on the development of different data mining techniques to extract actionable patterns from various types of log data in computing and BI systems. Four key problems—Log data categorization and event summarization, Leading indicator identification , Pattern prioritization by exploring the link structures , and Tensor model for three-way log data are studied. Case studies and comprehensive experiments on real application scenarios and datasets are conducted to show the effectiveness of our proposed approaches.

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as ƒ-test is performed during each node's split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

Research on the influence of behavioral forces that motivate trader behavior and sentiment- a prospect theory exegesis

This study focuses on empirical investigations and seeks implications by utilizing three different methodologies to test various aspects of trader behavior. The first methodology utilizes Prospect Theory to determine trader behavior during periods of extreme wealth contracting periods. Secondly, a threshold model to examine the sentiment variable is formulated and thirdly a study is made of the contagion effect and trader behavior. The connection between consumers' sense of financial well-being or sentiment and stock market performance has been studied at length. However, without data on actual versus experimental performance, implications based on this relationship are meaningless. The empirical agenda included examining a proprietary file of daily trader activities over a five-year period. Overall, during periods of extreme wealth altering conditions, traders "satisfice" rather than choose the "best" alternative. A trader's degree of loss aversion depends on his/her prior investment performance. A model that explains the behavior of traders during periods of turmoil is developed. Prospect Theory and the data file influenced the design of the model. Additional research included testing a model that permitted the data to signal the crisis through a threshold model. The third empirical study sought to investigate the existence of contagion caused by declining global wealth effects using evidence from the mining industry in Canada. Contagion, where a financial crisis begins locally and subsequently spreads elsewhere, has been studied in terms of correlations among similar regions. The results provide support for Prospect Theory in two out of the three empirical studies. The dissertation emphasizes the need for specifying precise, testable models of investors' expectations by providing tools to identify paradoxical behavior patterns. True enhancements in this field must include empirical research utilizing reliable data sources to mitigate data mining problems and allow researchers to distinguish between expectations-based and risk-based explanations of behavior. Through this type of research, it may be possible to systematically exploit "irrational" market behavior.

Ensemble Fuzzy Belief Intrusion Detection Design

With the rapid growth of the Internet, computer attacks are increasing at a fast pace and can easily cause millions of dollar in damage to an organization. Detecting these attacks is an important issue of computer security. There are many types of attacks and they fall into four main categories, Denial of Service (DoS) attacks, Probe, User to Root (U2R) attacks, and Remote to Local (R2L) attacks. Within these categories, DoS and Probe attacks continuously show up with greater frequency in a short period of time when they attack systems. They are different from the normal traffic data and can be easily separated from normal activities. On the contrary, U2R and R2L attacks are embedded in the data portions of the packets and normally involve only a single connection. It becomes difficult to achieve satisfactory detection accuracy for detecting these two attacks. Therefore, we focus on studying the ambiguity problem between normal activities and U2R/R2L attacks. The goal is to build a detection system that can accurately and quickly detect these two attacks. In this dissertation, we design a two-phase intrusion detection approach. In the first phase, a correlation-based feature selection algorithm is proposed to advance the speed of detection. Features with poor prediction ability for the signatures of attacks and features inter-correlated with one or more other features are considered redundant. Such features are removed and only indispensable information about the original feature space remains. In the second phase, we develop an ensemble intrusion detection system to achieve accurate detection performance. The proposed method includes multiple feature selecting intrusion detectors and a data mining intrusion detector. The former ones consist of a set of detectors, and each of them uses a fuzzy clustering technique and belief theory to solve the ambiguity problem. The latter one applies data mining technique to automatically extract computer users’ normal behavior from training network traffic data. The final decision is a combination of the outputs of feature selecting and data mining detectors. The experimental results indicate that our ensemble approach not only significantly reduces the detection time but also effectively detect U2R and R2L attacks that contain degrees of ambiguous information.

Integration and querying of heterogeneous, autonomous, distributed database systems

Today, databases have become an integral part of information systems. In the past two decades, we have seen different database systems being developed independently and used in different applications domains. Today's interconnected networks and advanced applications, such as data warehousing, data mining & knowledge discovery and intelligent data access to information on the Web, have created a need for integrated access to such heterogeneous, autonomous, distributed database systems. Heterogeneous/multidatabase research has focused on this issue resulting in many different approaches. However, a single, generally accepted methodology in academia or industry has not emerged providing ubiquitous intelligent data access from heterogeneous, autonomous, distributed information sources. This thesis describes a heterogeneous database system being developed at Highperformance Database Research Center (HPDRC). A major impediment to ubiquitous deployment of multidatabase technology is the difficulty in resolving semantic heterogeneity. That is, identifying related information sources for integration and querying purposes. Our approach considers the semantics of the meta-data constructs in resolving this issue. The major contributions of the thesis work include: (i.) providing a scalable, easy-to-implement architecture for developing a heterogeneous multidatabase system, utilizing Semantic Binary Object-oriented Data Model (Sem-ODM) and Semantic SQL query language to capture the semantics of the data sources being integrated and to provide an easy-to-use query facility; (ii.) a methodology for semantic heterogeneity resolution by investigating into the extents of the meta-data constructs of component schemas. This methodology is shown to be correct, complete and unambiguous; (iii.) a semi-automated technique for identifying semantic relations, which is the basis of semantic knowledge for integration and querying, using shared ontologies for context-mediation; (iv.) resolutions for schematic conflicts and a language for defining global views from a set of component Sem-ODM schemas; (v.) design of a knowledge base for storing and manipulating meta-data and knowledge acquired during the integration process. This knowledge base acts as the interface between integration and query processing modules; (vi.) techniques for Semantic SQL query processing and optimization based on semantic knowledge in a heterogeneous database environment; and (vii.) a framework for intelligent computing and communication on the Internet applying the concepts of our work.

Text Analytics of Social Media: Sentiment Analysis, Event Detection and Summarization

In the last decade, large numbers of social media services have emerged and been widely used in people's daily life as important information sharing and acquisition tools. With a substantial amount of user-contributed text data on social media, it becomes a necessity to develop methods and tools for text analysis for this emerging data, in order to better utilize it to deliver meaningful information to users. Previous work on text analytics in last several decades is mainly focused on traditional types of text like emails, news and academic literatures, and several critical issues to text data on social media have not been well explored: 1) how to detect sentiment from text on social media; 2) how to make use of social media's real-time nature; 3) how to address information overload for flexible information needs. In this dissertation, we focus on these three problems. First, to detect sentiment of text on social media, we propose a non-negative matrix tri-factorization (tri-NMF) based dual active supervision method to minimize human labeling efforts for the new type of data. Second, to make use of social media's real-time nature, we propose approaches to detect events from text streams on social media. Third, to address information overload for flexible information needs, we propose two summarization framework, dominating set based summarization framework and learning-to-rank based summarization framework. The dominating set based summarization framework can be applied for different types of summarization problems, while the learning-to-rank based summarization framework helps utilize the existing training data to guild the new summarization tasks. In addition, we integrate these techneques in an application study of event summarization for sports games as an example of how to better utilize social media data.

Utilizando comitês de classificadores para predição de rendimento escolar

Educational Data Mining is an application domain in artificial intelligence area that has been extensively explored nowadays. Technological advances and in particular, the increasing use of virtual learning environments have allowed the generation of considerable amounts of data to be investigated. Among the activities to be treated in this context exists the prediction of school performance of the students, which can be accomplished through the use of machine learning techniques. Such techniques may be used for student’s classification in predefined labels. One of the strategies to apply these techniques consists in their combination to design multi-classifier systems, which efficiency can be proven by results achieved in other studies conducted in several areas, such as medicine, commerce and biometrics. The data used in the experiments were obtained from the interactions between students in one of the most used virtual learning environments called Moodle. In this context, this paper presents the results of several experiments that include the use of specific multi-classifier systems systems, called ensembles, aiming to reach better results in school performance prediction that is, searching for highest accuracy percentage in the student’s classification. Therefore, this paper presents a significant exploration of educational data and it shows analyzes of relevant results about these experiments.

Internet of Things collaborativo: progettazione ed analisi di una piattaforma di aggregazione di dati sensoristici

Internet ha rivoluzionato il modo di comunicare degli individui. Siamo testimoni della nascita e dello sviluppo di un'era caratterizzata dalla disponibilità di informazione libera e accessibile a tutti. Negli ultimi anni grazie alla diffusione di smartphone, tablet e altre tipologie di dispositivi connessi, è cambiato il fulcro dell'innovazione spostandosi dalle persone agli oggetti. E' così che nasce il concetto di Internet of Things, termine usato per descrivere la rete di comunicazione creata tra i diversi dispositivi connessi ad Internet e capaci di interagire in autonomia. Gli ambiti applicativi dell'Internet of Things spaziano dalla domotica alla sanità, dall'environmental monitoring al concetto di smart cities e così via. L'obiettivo principale di tale disciplina è quello di migliorare la vita delle persone grazie a sistemi che siano in grado di interagire senza aver bisogno dell'intervento dell'essere umano. Proprio per la natura eterogenea della disciplina e in relazione ai diversi ambiti applicativi, nell'Internet of Things si può incorrere in problemi derivanti dalla presenza di tecnologie differenti o di modalità eterogenee di memorizzazione dei dati. A questo proposito viene introdotto il concetto di Internet of Things collaborativo, termine che indica l'obiettivo di realizzare applicazioni che possano garantire interoperabilità tra i diversi ecosistemi e tra le diverse fonti da cui l'Internet of Things attinge, sfruttando la presenza di piattaforme di pubblicazione di Open Data. L'obiettivo di questa tesi è stato quello di creare un sistema per l'aggregazione di dati da due piattaforme, ThingSpeak e Sparkfun, con lo scopo di unificarli in un unico database ed estrarre informazioni significative dai dati tramite due tecniche di Data Mining: il Dictionary Learning e l'Affinity Propagation. Vengono illustrate le due metodologie che rientrano rispettivamente tra le tecniche di classificazione e di clustering.

A compilation of global bio-optical in situ data for ocean-colour satellite applications

A compiled set of in situ data is important to evaluate the quality of ocean-colour satellite-data records. Here we describe the data compiled for the validation of the ocean-colour products from the ESA Ocean Colour Climate Change Initiative (OC-CCI). The data were acquired from several sources (MOBY, BOUSSOLE, AERONET-OC, SeaBASS, NOMAD, MERMAID, AMT, ICES, HOT, GeP&CO), span between 1997 and 2012, and have a global distribution. Observations of the following variables were compiled: spectral remote-sensing reflectances, concentrations of chlorophyll a, spectral inherent optical properties and spectral diffuse attenuation coefficients. The data were from multi-project archives acquired via the open internet services or from individual projects, acquired directly from data providers. Methodologies were implemented for homogenisation, quality control and merging of all data. No changes were made to the original data, other than averaging of observations that were close in time and space, elimination of some points after quality control and conversion to a standard format. The final result is a merged table designed for validation of satellite-derived ocean-colour products and available in text format. Metadata of each in situ measurement (original source, cruise or experiment, principal investigator) were preserved throughout the work and made available in the final table. Using all the data in a validation exercise increases the number of matchups and enhances the representativeness of different marine regimes. By making available the metadata, it is also possible to analyse each set of data separately.

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Towards Next Generation Vertical Search Engines

As the Web evolves unexpectedly fast, information grows explosively. Useful resources become more and more difficult to find because of their dynamic and unstructured characteristics. A vertical search engine is designed and implemented towards a specific domain. Instead of processing the giant volume of miscellaneous information distributed in the Web, a vertical search engine targets at identifying relevant information in specific domains or topics and eventually provides users with up-to-date information, highly focused insights and actionable knowledge representation. As the mobile device gets more popular, the nature of the search is changing. So, acquiring information on a mobile device poses unique requirements on traditional search engines, which will potentially change every feature they used to have. To summarize, users are strongly expecting search engines that can satisfy their individual information needs, adapt their current situation, and present highly personalized search results. In my research, the next generation vertical search engine means to utilize and enrich existing domain information to close the loop of vertical search engine's system that mutually facilitate knowledge discovering, actionable information extraction, and user interests modeling and recommendation. I investigate three problems in which domain taxonomy plays an important role, including taxonomy generation using a vertical search engine, actionable information extraction based on domain taxonomy, and the use of ensemble taxonomy to catch user's interests. As the fundamental theory, ultra-metric, dendrogram, and hierarchical clustering are intensively discussed. Methods on taxonomy generation using my research on hierarchical clustering are developed. The related vertical search engine techniques are practically used in Disaster Management Domain. Especially, three disaster information management systems are developed and represented as real use cases of my research work.