643 research outputs found
A learning Dempster-Shafer model for automated building detection
No full textThis paper presents a learning Dempster-Shafer model for the detection of buildings in aerial image and range data. The process of evidence assignment in the Dempster-Shafer method is implemented through membership functions in an adaptive network-based fuzzy inference system, where a back propagation learning rule is employed to tune the evidence assignment functions using training samples. The advantage of this method is that it incorporates our knowledge about various features that can be extracted from multi-source aerial data, and the evidence that these features provide for buildings and other objects in urban and suburban areas. Experimental results show that the proposed learning model improves the performance of the Dempster-Shafer classifier in detecting buildings in multi- source aerial data.Remote SensingAerospace Engineerin
Tratamento de imprecisão em sistemas especialistas
No full textDissertação (mestrado) - Universidade Federal de Santa Catarina, Centro Tecnológico, Programa de Pós-Graduação em Engenharia de Produção, Florianópolis, 1991.Esta dissertação apresenta um levantamento do estado da arte no Tratamento de Imprecisão em Sistemas Especialistas. Aborda-se o Raciocínio Humano na Resolução de Problemas e as principais técnicas existentes em tratamento de imprecisão em Inteligência Artificial: Método Bayesiano, Fatores de Certeza, Teoria da Evidência de Dempster e Shafer e Teoria dos Conjuntos Difusos. Para cada uma das técnicas estudadas são apresentados seus fundamentos teóricos, exemplos práticos e uma discussão sobre a performance entre as técnicas em relação aos principais requerimentos a uma técnica ideal no tratamento de imprecisão em Sistemas Especialistas
Robustness of the k-double auction under Knightian uncertainty
No full textThis dissertation considers the robustness of private value and common value k-double auctions when those markets are populated by regret minimizers. Regret minimizing agents, unlike typical expected utility maximizers, need not commit to a single prior in their decision rule. In fact, it is a feature of the minimax regret decision rule that is not based on any prior. This makes the decision rule an interesting one for agents who face Knightian Uncertainty. A decision problem involves Knightian uncertainty if the agents know the possible outcomes but not those outcomes' probabilities -- as may be the case in a new market. This dissertation shows that in a private value k-double auction, minimax regret traders will not converge to price-taking behavior as the market grows. Similarly, in a common value auction, traders' behavior may depend on the parameter k, but does not depend on the number of other traders in the market. The invariance of regret minimizing traders' strategies to the size of the markets they inhabit is not an accident of the sealed bid double auction institution. In fact, it is a consequence of the symmetry axiom. The final chapter in this dissertation shows that any agents in a k-double auction who use decision rules that accord with the symmetry axiom, then their bids and asks will not depend on the number of rival traders.Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-07-07 without embargo termsThe student, Rachel Shafer, accepted the attached license on 2016-04-14 at 16:53.The student, Rachel Shafer, submitted this Dissertation for approval on 2016-04-15 at 17:55.This Dissertation was approved for publication on 2016-04-20 at 10:16.DSpace SAF Submission Ingestion Package generated from Vireo submission #9230 on 2016-07-07 at 13:30:47Made available in DSpace on 2016-07-07T19:53:54Z (GMT). No. of bitstreams: 3
SHAFER-DISSERTATION-2016.pdf: 807035 bytes, checksum: e2582230400e5af3e42936bd2bea82f9 (MD5)
LICENSE.txt: 4210 bytes, checksum: be1cb1b8e16edbe137f2dc6c0f275ef0 (MD5)
PROQUEST_LICENSE.txt: 4556 bytes, checksum: 08a3543f048bc8c47c6e4b9503aa74f5 (MD5)
Previous issue date: 2016-04-2
Perspectives on the Theory and Practice of Belief Functions
No full textThe theory of belief functions provides one way to use mathematical probability in subjective judgment. It is a generalization of the Bayesian theory of subjective probability. When we use the Bayesian theory to quantify judgments about a question, we must assign probabilities to the possible answers to that question. The theory of belief functions is more flexible; it allows us to derive degrees of belief for a question from probabilities for a related question. These degrees of belief may or may not have the mathematical properties of probabilities; how much they differ from probabilities will depend on how closely the two questions are related. Examples of what we would now call belief-function reasoning can be found in the late seventeenth and early eighteenth centuries, well before Bayesian ideas were developed. In 1689, George Hooper gave rules for combining testimony that can be recognized as special cases of Dempster's rule for combining belief functions (Shafer 1986a). Similar rules were formulated by Jakob Bernoulli in his Ars Conjectandi, published posthumously in 1713, and by Johann-Heinrich Lambert in his Neues Organon, published in 1764 (Shafer 1978). Examples of belief-function reasoning can also be found in more recent work, by author
Uncertainty Modeling in Risk Assessment Based on Dempster–Shafer Theory of Evidence with Generalized Fuzzy Focal Elements
No full textAbstractDempster–Shafer theory of evidence is one of the important tools for decision making under uncertainty. It is more useful in situations when cost of technical difficulties is involved or uniqueness of the situation under study makes it difficult/impossible to cover enough observations to quantify the models with real data. Consequently, experts provide opinions in terms of basic probability assignment for focal elements. Usually, it is seen that experts provide basic probability assignment for interval (or crisp) focal elements. However, due to presence of uncertainty focal elements can sometimes be treated as normal/generalized triangular fuzzy number (TFN in short) instead of intervals or crisp sets. TFN encodes only most likely value (mode) and the spread. This paper presents an attempt to combine Dempster–Shafer structures (DSS in short) with generalized/normal fuzzy focal elements using possibilistic sampling technique. To this end, human health risk assessment is carried out under such setting
Bayesian and Dempster–Shafer reasoning for knowledge-based fault diagnosis: A comparative study
No full textEven though various frameworks exist for reasoning under uncertainty, a realistic fault diagnosis task does not fit into any of them in a straightforward way. For each framework, only part of the available data and knowledge is in the desired format. Moreover, additional criteria, like clarity of inference and computational efficiency, require trade-offs to be made. Finally, fault diagnosis is usually just a subpart of a larger process, e.g. condition-based maintenance. Consequently, the final goal of fault diagnosis is not (just) decision making, and the outcome of the diagnosis process should be a suitable input for the subsequent reasoning process. In this paper, we analyze how a knowledge-based diagnosis task is influenced by uncertainty, investigate which additional objectives are of relevance, and compare how these characteristics and objectives are handled in two well-known frameworks, namely the Bayesian and the Dempster-Shafer reasoning framework. In contrast to previous works, which take the reasoning method as the starting point, we start from the application, knowledge-based fault diagnosis, and examine the effectiveness of different reasoning methods for this specific application. It is concluded that the suitability of each reasoning method highly depends on the problem under consideration and on the requirements of the user. The best framework can only be assigned given that the problem (including uncertainty characteristics) and the user requirements are completely known.Accepted Author ManuscriptTeam Bart De SchutterLearning & Autonomous Contro
Medicaid policy data for evaluating eligibility and programmatic changes
No full textMedicaid and the Children's Health Insurance Program (CHIP) provide health insurance coverage to approximately 85 million Americans as of late 2023. There is substantial variation in eligibility criteria, application procedures, premiums, and other programmatic characteristics across states and over time. Analyzing changes in Medicaid policies is important for state and federal agencies and other stakeholders, but such analysis requires data on historical programmatic characteristics that are often not available in a form ready for quantitative analysis. Our objective is to fill this gap by synthesizing existing qualitative policy data to create a new data resource that facilitates Medicaid policy research.
Our source data were the 50-state surveys of Medicaid and CHIP eligibility, enrollment, and cost-sharing policies conducted near annually by KFF since 2000, which we originally coded through 2020. These reports are a rich source of point-in-time information but not operationalized for quantitative analysis. Through a review of the measures captured in the KFF surveys, we developed five Medicaid policy domains with 122 measures in total, with each coded by state-quarter—1) eligibility (28 measures), 2) enrollment and renewal processes (39), 3) premiums (16), 4) cost-sharing (26), and 5) managed care (13).
1 (June 28, 2023) – original version
2 (March 14, 2024) – re-reviewed, corrected (where necessary), and extended five income eligibility measures (inc_inf, inc_child_1_5, inc_child_6_18, inc_parents, and inc_preg) through January 202
A systematic analysis of extinction at 3 months of age
No full textIn operant conditioning, "extinction" refers to a procedure in which reinforcement is consistently withheld after conditioned responding. The "extinction effect" is observed when learned responding declines to its baserate, or extinguishes. Evidence suggests that the original association is preserved through extinction because conditioned responding can be restored. A hallmark of extinction is that it dissipates with time, and as subjects again exhibit the conditioned response. This phenomenon, spontaneous recovery, led Pavlov (1927) to conclude that learning is permanent. Extinction manipulations have been used in research with infants to eliminate undesirable behavior, to study emotion, and as test periods in instrumental learning preparations. However, it is unknown whether the properties of extinction are the same for human infants as for human adults and nonhuman animals.
In order to systematically characterize the extinction process early in ontogeny, 3-month-olds were first trained using the mobile conjugate reinforcement paradigm to kick to move an overhead mobile. Once the response was acquired, the extinction was presented and spontaneous recovery was assessed over the course of the normal retention interval for the task. The duration and temporal placement of the extinction phase were manipulated.
Infants did not reduce ongoing responding during the extinction manipulation, but the extinction effect was evident during subsequent testing. More than three minutes of nonreinforcement immediately following acquisition was effective at decreasing conditioned responding during subsequent long-term retention test. Paradoxically, when the extinction session was separated from acquisition by at least one day, 3 min was sufficient to cause a reduction in conditioned responding, while 6 min enhanced retention. No evidence of spontaneous recovery was observed in this study.M.S.Includes bibliographical references (p. 44-52)
- …
