Statistical Dialog Management for Health Interventions

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.

Biogeochemical, sedimentological and isotopic sediment record of Lake Dojran

A Late Glacial to Holocene sediment sequence (Co1260, 717 cm) from Lake Dojran, located at the boarder of the F.Y.R. of Macedonia and Greece, has been investigated to provide information on climate variability in the Balkan region. A robust age-model was established from 13 radiocarbon ages, and indicates that the base of the sequence was deposited at ca. 12 500 cal yr BP, when the lake-level was low. Variations in sedimentological (H2O, TOC, CaCO3, TS, TOC/TN, TOC/TS, grain-size, XRF, d18Ocarb, d13Ccarb, d13Corg) data were linked to hydro-acoustic data and indicate that warmer and more humid climate conditions characterised the remaining period of the Younger Dryas until the beginning of the Holocene. The Holocene exhibits significant environmental variations, including the 8.2 and 4.2 ka cooling events, the Medieval Warm Period and the Little Ice Age. Human induced erosion processes in the catchment of Lake Dojran intensified after 2800 cal yr BP.

Highway Performance and Time-Sensitive Industries, 1998

This report addresses delays to freight shippers. Although the focus is on just-in-time (JIT) businesses, the authors also note that non JIT businesses also suffer delays that impact their productivity. The table of contents lists the following headings: chapter 1 - introduction - a trial application: the Des Moines metropolitan area; structure of the report; chapter 2 - reliability at the forefront of freight transport demand - manufacturing and inventory; just-in-time operations in the U.S.; transportation consequences; summary; chapter 3 - JIT operations in Iowa - survey and sample; trucking activity and service; just-in-time truck transportation in Iowa; assessment of factors affecting truck transportation service; summary and conclusions; chapter 4 - travel time uncertainty induced by incidents - a probabilistic model for incident occurrences and durations; calculation of delay; trial application; conclusions; and chapter 5 - conclusions and recommendations - conclusions; recommendations.

Learning to Interpret and Generate Instructional Recipes

Thesis (Ph.D.)--University of Washington, 2016-08

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Biologia reprodutiva, crescimento corporal e parâmetros demográficos de Cavia magna em uma ilha estuarina do extremo sul do Brasil

A teoria da história de vida tem como objetivo compreender os fatores que produzem variações na taxa de sobrevivência, tamanho no nascimento, idade de maturação, sazonalidade na reprodução, longevidade, razão sexual da prole. O gênero Cavia pallas 1776 apresenta a maior distribuição dentro da subfamília Cavinae, sendo composto por seis espécies, dentre elas Cavia magna, a qual habita regiões de restinga próximas a estuários ou lagos do norte do Uruguai ao sul do Brasil. Durante esse trabalho avaliamos os padrões da história de vida de uma população de Cavia magna da Ilha dos Marinheiros, RS, Brasil, devido ao fato de se tratar de uma espécie com baixa taxa reprodutiva, distribuição geográfica restrita, e estar exposta a alta pressão de predação. Para isso foi realizado um programa de captura-marcação-recaptura, durante 13 meses no qual foram capturados 129 animais, sendo 63 fêmeas e 66 machos. As longevidades máximas registradas, foram 233 dias para uma fêmea e 321 dias para um macho. Foram encontradas 13 fêmeas grávidas ou lactantes, dentre elas 9 estavam grávidas, sendo que 6 estavam prenhas de 2 filhotes e 3 estavam prenhas de 1 filhote apenas. Vários parâmetros foram testados, para estimar a taxa de sobrevivência e captura ,utilizamos o programa Mark, o método jacknife um modelo probabilístico, que permite heterogeneidade individual nas taxas de captura também foi utilizado. Não houve diferenças significativas no número de machos e fêmeas, a razão sexual foi 1:1. Em relação a estrutura etária, a população foi composta por adultos (82%) e a densidade populacional foi de 30 animais por hectare.

An Estimation of Distribution Algorithm with Intelligent Local Search for Rule-based Nurse Rostering

This paper proposes a new memetic evolutionary algorithm to achieve explicit learning in rule-based nurse rostering, which involves applying a set of heuristic rules for each nurse's assignment. The main framework of the algorithm is an estimation of distribution algorithm, in which an ant-miner methodology improves the individual solutions produced in each generation. Unlike our previous work (where learning is implicit), the learning in the memetic estimation of distribution algorithm is explicit, i.e. we are able to identify building blocks directly. The overall approach learns by building a probabilistic model, i.e. an estimation of the probability distribution of individual nurse-rule pairs that are used to construct schedules. The local search processor (i.e. the ant-miner) reinforces nurse-rule pairs that receive higher rewards. A challenging real world nurse rostering problem is used as the test problem. Computational results show that the proposed approach outperforms most existing approaches. It is suggested that the learning methodologies suggested in this paper may be applied to other scheduling problems where schedules are built systematically according to specific rules.

An Estimation of Distribution Algorithm with Intelligent Local Search for Rule-based Nurse Rostering

This paper proposes a new memetic evolutionary algorithm to achieve explicit learning in rule-based nurse rostering, which involves applying a set of heuristic rules for each nurse's assignment. The main framework of the algorithm is an estimation of distribution algorithm, in which an ant-miner methodology improves the individual solutions produced in each generation. Unlike our previous work (where learning is implicit), the learning in the memetic estimation of distribution algorithm is explicit, i.e. we are able to identify building blocks directly. The overall approach learns by building a probabilistic model, i.e. an estimation of the probability distribution of individual nurse-rule pairs that are used to construct schedules. The local search processor (i.e. the ant-miner) reinforces nurse-rule pairs that receive higher rewards. A challenging real world nurse rostering problem is used as the test problem. Computational results show that the proposed approach outperforms most existing approaches. It is suggested that the learning methodologies suggested in this paper may be applied to other scheduling problems where schedules are built systematically according to specific rules.

Learning Binary Code Representations for Effective and Efficient Image Retrieval

The size of online image datasets is constantly increasing. Considering an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary strings, have become very popular because of their high efficiency in search and storage capacity. In the first part, we propose a multimodal retrieval method based on latent feature models. The procedure consists of a nonparametric Bayesian framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal queries and an extension model for relevance feedback. In the second part, we focus on supervised hashing with kernels. We describe a flexible hashing procedure that treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present a scalable inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and distributed computing. In the last part, we define an incremental hashing strategy for dynamic databases where new images are added to the databases frequently. The method is based on a two-stage classification framework using binary and multi-class SVMs. The proposed method also enforces balance in binary codes by an imbalance penalty to obtain higher quality binary codes. We learn hash functions by an efficient algorithm where the NP-hard problem of finding optimal binary codes is solved via cyclic coordinate descent and SVMs are trained in a parallelized incremental manner. For modifications like adding images from an unseen class, we propose an incremental procedure for effective and efficient updates to the previous hash functions. Experiments on three large-scale image datasets demonstrate that the incremental strategy is capable of efficiently updating hash functions to the same retrieval performance as hashing from scratch.

Koherentziazko diskurtso erlazioen detekzio automatikoa patroien bidez, XMLko erlazio-egiturak oinarri hartuta

[EU]Hizkuntzaren prozesamenduan testu koherenteetan kausa taldeko erlazioak (KAUSA, ONDORIOA eta HELBURUA) automatikoki hautematea eta bereiztea erabilgarria da galdera-erantzun automatikoko sistemak eraikitzerako orduan. Horretarako Egitura Erretorikoaren Teoria (Rhetorical Structure Theory, aurrerantzean RST) eta bere erlazioak erabiliko ditugu, corpus bezala RST Treebank -a (Iruskieta et al., 2013) hartuta, zientziako laburpen-testuz osatutako corpusa, hain zuzen ere. Corpus hori XML formatuan deskargatu eta hortik XPATH tresnaren bidez informazio garrantzitsuena eskuratzen dugu. Lan honek 3 helburu nagusi ditu: lehendabizi, kausa taldeko erlazioak elkarren artean bereiztea, bigarrenez, kausa taldeko erlazio hauek beste erlazio guztiekin bereiztea, eta azkenik, EBALUAZIOA eta INTERPRETAZIOA erlazioak bereiztea sentimendu analisian aplikatu ahal izateko. Ataza horiek egiteko, RhetDB tresnarekin eskuratu diren patroi ensaguratsuenak erabili eta bi aplikazio garatu ditugu. Alde batetik, bilatu nahi ditugun patroiak adierazi eta erlazio-egitura duen edonolako testuetan bilaketak egiten dituen bilatzailea, eta bestetik, patroi esanguratsuenak emanda erlazioak etiketatzen dituen etiketatzailea. Bi aplikazio hauek gainera, ahalik eta modu parametrizagarrienean erabiltzeko garatu ditugu, kodea aldatu gabe edonork erabili ahal izateko antzeko atazak egiteko. Etiketatzaileak ebaluatu ondoren, identifikatzeko erlaziorik errazena HELBURUA erlazioa dela ikusi dugu eta KAUSA eta ONDORIOA bereizteko arazo gehiago dauzkagula ere ondorioztatu dugu. Modu berean, EBALUAZIOA eta INTERPRETAZIOA ere elkarren artean bereiz dezakegula ikusi dugu.

Políticas de geração distribuída e sustentabilidade do sistema elétrico

Tese (doutorado)—Universidade de Brasília, Centro de Desenvolvimento Sustentável, 2015.

SAMPLING BIAS IN EVALUATING THE PROBABILITY OF SEISMICALLY INDUCED SOIL LIQUEFACTION WITH SPT & CPT CASE HISTORIES

Several deterministic and probabilistic methods are used to evaluate the probability of seismically induced liquefaction of a soil. The probabilistic models usually possess some uncertainty in that model and uncertainties in the parameters used to develop that model. These model uncertainties vary from one statistical model to another. Most of the model uncertainties are epistemic, and can be addressed through appropriate knowledge of the statistical model. One such epistemic model uncertainty in evaluating liquefaction potential using a probabilistic model such as logistic regression is sampling bias. Sampling bias is the difference between the class distribution in the sample used for developing the statistical model and the true population distribution of liquefaction and non-liquefaction instances. Recent studies have shown that sampling bias can significantly affect the predicted probability using a statistical model. To address this epistemic uncertainty, a new approach was developed for evaluating the probability of seismically-induced soil liquefaction, in which a logistic regression model in combination with Hosmer-Lemeshow statistic was used. This approach was used to estimate the population (true) distribution of liquefaction to non-liquefaction instances of standard penetration test (SPT) and cone penetration test (CPT) based most updated case histories. Apart from this, other model uncertainties such as distribution of explanatory variables and significance of explanatory variables were also addressed using KS test and Wald statistic respectively. Moreover, based on estimated population distribution, logistic regression equations were proposed to calculate the probability of liquefaction for both SPT and CPT based case history. Additionally, the proposed probability curves were compared with existing probability curves based on SPT and CPT case histories.

Using a Dialogue Manager to Improve Semantic Web Search

Question Answering systems that resort to the Semantic Web as a knowledge base can go well beyond the usual matching words in documents and, preferably, find a precise answer, without requiring user help to interpret the documents returned. In this paper, the authors introduce a Dialogue Manager that, through the analysis of the question and the type of expected answer, provides accurate answers to the questions posed in Natural Language. The Dialogue Manager not only represents the semantics of the questions, but also represents the structure of the discourse, including the user intentions and the questions context, adding the ability to deal with multiple answers and providing justified answers. The authors’ system performance is evaluated by comparing with similar question answering systems. Although the test suite is slight dimension, the results obtained are very promising.

Abstractive Long Document Summarization: Studio e Sperimentazione di Modelli Generativi Retrieval-Augmented

In questa tesi si trattano lo studio e la sperimentazione di un modello generativo retrieval-augmented, basato su Transformers, per il task di Abstractive Summarization su lunghe sentenze legali. La sintesi automatica del testo (Automatic Text Summarization) è diventata un task di Natural Language Processing (NLP) molto importante oggigiorno, visto il grandissimo numero di dati provenienti dal web e banche dati. Inoltre, essa permette di automatizzare un processo molto oneroso per gli esperti, specialmente nel settore legale, in cui i documenti sono lunghi e complicati, per cui difficili e dispendiosi da riassumere. I modelli allo stato dell’arte dell’Automatic Text Summarization sono basati su soluzioni di Deep Learning, in particolare sui Transformers, che rappresentano l’architettura più consolidata per task di NLP. Il modello proposto in questa tesi rappresenta una soluzione per la Long Document Summarization, ossia per generare riassunti di lunghe sequenze testuali. In particolare, l’architettura si basa sul modello RAG (Retrieval-Augmented Generation), recentemente introdotto dal team di ricerca Facebook AI per il task di Question Answering. L’obiettivo consiste nel modificare l’architettura RAG al fine di renderla adatta al task di Abstractive Long Document Summarization. In dettaglio, si vuole sfruttare e testare la memoria non parametrica del modello, con lo scopo di arricchire la rappresentazione del testo di input da riassumere. A tal fine, sono state sperimentate diverse configurazioni del modello su diverse tipologie di esperimenti e sono stati valutati i riassunti generati con diverse metriche automatiche.

A formal analysis of blockchain consensus

In this thesis, we analyse these protocols using PRISM+, our extension of the probabilistic model checker PRISM with blockchain types and operations upon them. This allows us to model the behaviour of key participants in the protocols and describe the protocols as a parallel composition of PRISM+ processes. Through our analysis of the Bitcoin model, we are able to understand how forks (where different nodes have different versions of the blockchain) occur and how they depend on specific parameters of the protocol, such as the difficulty of the cryptopuzzle and network communication delays. Our results corroborate the statement that considering confirmed the transactions in blocks at depth larger than 5 is reasonable because the majority of miners have consistent blockchains up-to that depth with probability of almost 1. We also study the behaviour of the Bitcoin network with churn miners (nodes that leave and rejoin the network) and with different topologies (linear topology, ring topology, tree topology and fully connected topology). PRISM+ is therefore used to analyse the resilience of Hybrid Casper when changing various basic parameters of the protocol, such as block creation rates and penalty determination strategies. We also study the robustness of Hybrid Casper against two known attacks: the Eclipse attack (where an attacker controls a significant portion of the network's nodes and can prevent other nodes from receiving new transactions) and the majority attack (where an attacker controls a majority of the network's nodes and can manipulate the blockchain to their advantage).