Data-Driven Wildfire Propagation Modeling with FARSITE-EnKF

The goal of this study is to provide a framework for future researchers to understand and use the FARSITE wildfire-forecasting model with data assimilation. Current wildfire models lack the ability to provide accurate prediction of fire front position faster than real-time. When FARSITE is coupled with a recursive ensemble filter, the data assimilation forecast method improves. The scope includes an explanation of the standalone FARSITE application, technical details on FARSITE integration with a parallel program coupler called OpenPALM, and a model demonstration of the FARSITE-Ensemble Kalman Filter software using the FireFlux I experiment by Craig Clements. The results show that the fire front forecast is improved with the proposed data-driven methodology than with the standalone FARSITE model.

Learning data-driven models of non-verbal behaviors for building rapport using an intelligent virtual agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness.^ Evidence-based patient-centered Brief Motivational Interviewing (BMI) interventions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary.^ Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems.^ To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].^

Data-driven and data-oriented methods for materials science and technologies

The discovery of new materials and their functions has always been a fundamental component of technological progress. Nowadays, the quest for new materials is stronger than ever: sustainability, medicine, robotics and electronics are all key assets which depend on the ability to create specifically tailored materials. However, designing materials with desired properties is a difficult task, and the complexity of the discipline makes it difficult to identify general criteria. While scientists developed a set of best practices (often based on experience and expertise), this is still a trial-and-error process. This becomes even more complex when dealing with advanced functional materials. Their properties depend on structural and morphological features, which in turn depend on fabrication procedures and environment, and subtle alterations leads to dramatically different results. Because of this, materials modeling and design is one of the most prolific research fields. Many techniques and instruments are continuously developed to enable new possibilities, both in the experimental and computational realms. Scientists strive to enforce cutting-edge technologies in order to make progress. However, the field is strongly affected by unorganized file management, proliferation of custom data formats and storage procedures, both in experimental and computational research. Results are difficult to find, interpret and re-use, and a huge amount of time is spent interpreting and re-organizing data. This also strongly limit the application of data-driven and machine learning techniques. This work introduces possible solutions to the problems described above. Specifically, it talks about developing features for specific classes of advanced materials and use them to train machine learning models and accelerate computational predictions for molecular compounds; developing method for organizing non homogeneous materials data; automate the process of using devices simulations to train machine learning models; dealing with scattered experimental data and use them to discover new patterns.

Data-driven multivariate flood hazard modeling

The present Dissertation shows how recent statistical analysis tools and open datasets can be exploited to improve modelling accuracy in two distinct yet interconnected domains of flood hazard (FH) assessment. In the first Part, unsupervised artificial neural networks are employed as regional models for sub-daily rainfall extremes. The models aim to learn a robust relation to estimate locally the parameters of Gumbel distributions of extreme rainfall depths for any sub-daily duration (1-24h). The predictions depend on twenty morphoclimatic descriptors. A large study area in north-central Italy is adopted, where 2238 annual maximum series are available. Validation is performed over an independent set of 100 gauges. Our results show that multivariate ANNs may remarkably improve the estimation of percentiles relative to the benchmark approach from the literature, where Gumbel parameters depend on mean annual precipitation. Finally, we show that the very nature of the proposed ANN models makes them suitable for interpolating predicted sub-daily rainfall quantiles across space and time-aggregation intervals. In the second Part, decision trees are used to combine a selected blend of input geomorphic descriptors for predicting FH. Relative to existing DEM-based approaches, this method is innovative, as it relies on the combination of three characteristics: (1) simple multivariate models, (2) a set of exclusively DEM-based descriptors as input, and (3) an existing FH map as reference information. First, the methods are applied to northern Italy, represented with the MERIT DEM (∼90m resolution), and second, to the whole of Italy, represented with the EU-DEM (25m resolution). The results show that multivariate approaches may (a) significantly enhance flood-prone areas delineation relative to a selected univariate one, (b) provide accurate predictions of expected inundation depths, (c) produce encouraging results in extrapolation, (d) complete the information of imperfect reference maps, and (e) conveniently convert binary maps into continuous representation of FH.

Data-driven Signal Processing per Jamming Detection in Sistemi Satellitari

In questo elaborato vengono analizzate differenti tecniche per la detection di jammer attivi e costanti in una comunicazione satellitare in uplink. Osservando un numero limitato di campioni ricevuti si vuole identificare la presenza di un jammer. A tal fine sono stati implementati i seguenti classificatori binari: support vector machine (SVM), multilayer perceptron (MLP), spectrum guarding e autoencoder. Questi algoritmi di apprendimento automatico dipendono dalle features che ricevono in ingresso, per questo motivo è stata posta particolare attenzione alla loro scelta. A tal fine, sono state confrontate le accuratezze ottenute dai detector addestrati utilizzando differenti tipologie di informazione come: i segnali grezzi nel tempo, le statistical features, le trasformate wavelet e lo spettro ciclico. I pattern prodotti dall’estrazione di queste features dai segnali satellitari possono avere dimensioni elevate, quindi, prima della detection, vengono utilizzati i seguenti algoritmi per la riduzione della dimensionalità: principal component analysis (PCA) e linear discriminant analysis (LDA). Lo scopo di tale processo non è quello di eliminare le features meno rilevanti, ma combinarle in modo da preservare al massimo l’informazione, evitando problemi di overfitting e underfitting. Le simulazioni numeriche effettuate hanno evidenziato come lo spettro ciclico sia in grado di fornire le features migliori per la detection producendo però pattern di dimensioni elevate, per questo motivo è stato necessario l’utilizzo di algoritmi di riduzione della dimensionalità. In particolare, l'algoritmo PCA è stato in grado di estrarre delle informazioni migliori rispetto a LDA, le cui accuratezze risentivano troppo del tipo di jammer utilizzato nella fase di addestramento. Infine, l’algoritmo che ha fornito le prestazioni migliori è stato il Multilayer Perceptron che ha richiesto tempi di addestramento contenuti e dei valori di accuratezza elevati.

A Topological Approach to Fuzzy Sets

This thesis presents a topological approach to studying fuzzy setsby means of modifier operators. Modifier operators are mathematical models, e.g., for hedges, and we present briefly different approaches to studying modifier operators. We are interested in compositional modifier operators, modifiers for short, and these modifiers depend on binary relations. We show that if a modifier depends on a reflexive and transitive binary relation on U, then there exists a unique topology on U such that this modifier is the closure operator in that topology. Also, if U is finite then there exists a lattice isomorphism between the class of all reflexive and transitive relations and the class of all topologies on U. We define topological similarity relation "≈" between L-fuzzy sets in an universe U, and show that the class LU/ ≈ is isomorphic with the class of all topologies on U, if U is finite and L is suitable. We consider finite bitopological spaces as approximation spaces, and we show that lower and upper approximations can be computed by means of α-level sets also in the case of equivalence relations. This means that approximations in the sense of Rough Set Theory can be computed by means of α-level sets. Finally, we present and application to data analysis: we study an approach to detecting dependencies of attributes in data base-like systems, called information systems.

Hybrid Artificial Intelligence to Extract Patterns and Rules from Argumentative and Legal Texts

This Thesis is composed of a collection of works written in the period 2019-2022, whose aim is to find methodologies of Artificial Intelligence (AI) and Machine Learning to detect and classify patterns and rules in argumentative and legal texts. We define our approach “hybrid”, since we aimed at designing hybrid combinations of symbolic and sub-symbolic AI, involving both “top-down” structured knowledge and “bottom-up” data-driven knowledge. A first group of works is dedicated to the classification of argumentative patterns. Following the Waltonian model of argument and the related theory of Argumentation Schemes, these works focused on the detection of argumentative support and opposition, showing that argumentative evidences can be classified at fine-grained levels without resorting to highly engineered features. To show this, our methods involved not only traditional approaches such as TFIDF, but also some novel methods based on Tree Kernel algorithms. After the encouraging results of this first phase, we explored the use of a some emerging methodologies promoted by actors like Google, which have deeply changed NLP since 2018-19 — i.e., Transfer Learning and language models. These new methodologies markedly improved our previous results, providing us with best-performing NLP tools. Using Transfer Learning, we also performed a Sequence Labelling task to recognize the exact span of argumentative components (i.e., claims and premises), thus connecting portions of natural language to portions of arguments (i.e., to the logical-inferential dimension). The last part of our work was finally dedicated to the employment of Transfer Learning methods for the detection of rules and deontic modalities. In this case, we explored a hybrid approach which combines structured knowledge coming from two LegalXML formats (i.e., Akoma Ntoso and LegalRuleML) with sub-symbolic knowledge coming from pre-trained (and then fine-tuned) neural architectures.

Improving discovery in the life sciences using semantic Web technologies and linked data: design principles for life sciences knowledge organization systems

Dissertation presented to obtain the Ph.D degree in Bioinformatics

Acquiring expert knowledge for the design of conceptual information systems

Conceptual Information Systems unfold the conceptual structure of data stored in relational databases. In the design phase of the system, conceptual hierarchies have to be created which describe different aspects of the data. In this paper, we describe two principal ways of designing such conceptual hierarchies, data driven design and theory driven design and discuss advantages and drawbacks. The central part of the paper shows how Attribute Exploration, a knowledge acquisition tool developped by B. Ganter can be applied for narrowing the gap between both approaches.

Tokamak TCABR: Acquisition system, data analysis, and remote participation using MDSplus

Each plasma physics laboratory has a proprietary scheme to control and data acquisition system. Usually, it is different from one laboratory to another. It means that each laboratory has its own way to control the experiment and retrieving data from the database. Fusion research relies to a great extent on international collaboration and this private system makes it difficult to follow the work remotely. The TCABR data analysis and acquisition system has been upgraded to support a joint research programme using remote participation technologies. The choice of MDSplus (Model Driven System plus) is proved by the fact that it is widely utilized, and the scientists from different institutions may use the same system in different experiments in different tokamaks without the need to know how each system treats its acquisition system and data analysis. Another important point is the fact that the MDSplus has a library system that allows communication between different types of language (JAVA, Fortran, C, C++, Python) and programs such as MATLAB, IDL, OCTAVE. In the case of tokamak TCABR interfaces (object of this paper) between the system already in use and MDSplus were developed, instead of using the MDSplus at all stages, from the control, and data acquisition to the data analysis. This was done in the way to preserve a complex system already in operation and otherwise it would take a long time to migrate. This implementation also allows add new components using the MDSplus fully at all stages. (c) 2012 Elsevier B.V. All rights reserved.

Knowledge management in multinational companies: the repatriates’ role in the competitive advantage in subsidiaries

This paper addresses the topic of knowledge management in multinational companies (MNCs). Its purpose is to examine the role of expatriates in knowledge acquisition and transfer within MNCs. Specifically it focuses on knowledge acquisition and transfer from one MNC head office located in Germany to two Portuguese subsidiaries as a basis for competitive advantage in their Portuguese subsidiaries. A qualitative research methodology is used, specifically through an exploratory case study approach, which examines how international assignments are important for the role of expatriates In knowledge acquisition and transfer between foreign head offices and their Portuguese subsidiaries. The data were collected through semi structured interviews to 10 Portuguese repatriates from two Portuguese subsidiaries of one foreign MNC. The findings suggest that the reasons that lead to expatriating employees from Portuguese subsidiaries to foreign head offices are connected to (1) knowledge management strategies to development the subsidiary’s performance; (2) new skills and knowledge acquisition by future team leaders and business/product managers in Portuguese subsidiaries; (3) procuring knowledge, from agents in head office, to be disseminated amongst co-workers in Portuguese subsidiaries; (4) acquiring global management skills, impossible to acquire locally and; (5) developing global projects within MNC. Also our results show that knowledge acquisition and transfer from foreign head office, through subsidiaries’ expatriates, contributes directly to the Portuguese subsidiaries’ innovation, improved performance, competitive advantage and growth in the economic sectors in which they operate. Moreover, evidence reveals that expatriation is seen as a strategy to fulfil some of the main organisational objectives through their expatriates (e.g., create new products and business markets, develop and incorporate new organisational techniques and processes, integrate global teams within multinational corporation with a responsibility on the definition of global objectives). The results obtained suggest that expatriates have a central role in acquiring and transferring strategic knowledge from MNC head office to their subsidiaries located in Portugal. Based on the findings, the paper discusses in detail the main theoretical and managerial implications. Suggestions for further research are also presented. The study’s main limitation is the small size of the sample, but its findings and methodology are quite original and significant.

AWSum-Combining Classification with Knowledge Aquisition

Many classifiers achieve high levels of accuracy but have limited applicability in real world situations because they do not lead to a greater understanding or insight into the^way features influence the classification. In areas such as health informatics a classifier that clearly identifies the influences on classification can be used to direct research and formulate interventions. This research investigates the practical applications of Automated Weighted Sum, (AWSum), a classifier that provides accuracy comparable to other techniques whilst providing insight into the data. This is achieved by calculating a weight for each feature value that represents its influence on the class value. The merits of this approach in classification and insight are evaluated on a Cystic Fibrosis and Diabetes datasets with positive results.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

On the innovation capacity of technologyrelated knowledge-intensive business services. A case study of the technology and engineering consulting (TEC) sector in Singapore

Even though the research on innovation in services has expanded remarkably especially during the past two decades, there is still a need to increase understanding on the special characteristics of service innovation. In addition to studying innovation in service companies and industries, research has also recently focused more on services in innovation, as especially the significance of so-called knowledge intensive business services (KIBS) for the competitive edge of their clients, othercompanies, regions and even nations has been proved in several previous studies. This study focuses on studying technology-based KIBS firms, and technology andengineering consulting (TEC) sector in particular. These firms have multiple roles in innovation systems, and thus, there is also a need for in-depth studies that increase knowledge about the types and dimensions of service innovations as well as underlying mechanisms and procedures which make the innovations successful. The main aim of this study is to generate new knowledge in the fragmented research field of service innovation management by recognizing the different typesof innovations in TEC services and some of the enablers of and barriers to innovation capacity in the field, especially from the knowledge management perspective. The study also aims to shed light on some of the existing routines and new constructions needed for enhancing service innovation and knowledge processing activities in KIBS companies of the TEC sector. The main samples of data in this research include literature reviews and public data sources, and a qualitative research approach with exploratory case studies conducted with the help of the interviews at technology consulting companies in Singapore in 2006. These complement the qualitative interview data gathered previously in Finland during a larger research project in the years 2004-2005. The data is also supplemented by a survey conducted in Singapore. The respondents for the survey by Tan (2007) were technology consulting companies who operate in the Singapore region. The purpose ofthe quantitative part of the study was to validate and further examine specificaspects such as the influence of knowledge management activities on innovativeness and different types of service innovations, in which the technology consultancies are involved. Singapore is known as a South-east Asian knowledge hub and is thus a significant research area where several multinational knowledge-intensive service firms operate. Typically, the service innovations identified in the studied TEC firms were formed by several dimensions of innovations. In addition to technological aspects, innovations were, for instance, related to new client interfaces and service delivery processes. The main enablers of and barriers to innovation seem to be partly similar in Singaporean firms as compared to the earlier study of Finnish TEC firms. Empirical studies also brought forth the significance of various sources of knowledge and knowledge processing activities as themain driving forces of service innovation in technology-related KIBS firms. A framework was also developed to study the effect of knowledge processing capabilities as well as some moderators on the innovativeness of TEC firms. Especially efficient knowledge acquisition and environmental dynamism seem to influence the innovativeness of TEC firms positively. The results of the study also contributeto the present service innovation literature by focusing more on 'innovation within KIBs' rather than 'innovation through KIBS', which has been the typical viewpoint stressed in the previous literature. Additionally, the study provides several possibilities for further research.