Incidence calculus: A mechanism for probabilistic reasoning

Mechanisms for the automation of uncertainty are required for expert systems. Sometimes these mechanisms need to obey the properties of probabilistic reasoning. We argue that a purely numeric mechanism, like those proposed so far, cannot provide a probabilistic logic with truth functional connectives. We propose an alternative mechanism, Incidence Calculus, which is based on a representation of uncertainty using sets of points, which might represent situations models or possible worlds. Incidence Calculus does provide a probabilistic logic with truth functional connectives.     

A probabilistic language formalism for stochastic discrete-eventsystems

The formalism of probabilistic languages has been introduced for modeling the qualitative behavior of stochastic discrete-event systems. A probabilistic language is a unit interval-valued map over the set of traces of the system satisfying certain consistency constraints. Regular language operators such as choice, concatenation, and Kleene-closure have been defined in the setting of probabilistic languages to allow modeling of complex systems in terms of simpler ones. The set of probabilistic languages is closed under such operators, thus forming an algebra. It also is a complete partial order under a natural ordering in which the operators are continuous. Hence, recursive equations can be solved in this algebra. This is alternatively derived by using the contraction mapping theorem on the set of probabilistic languages which is shown to be a complete metric space. The notion of regularity, i.e., finiteness of automata representation, of probabilistic languages has been defined and it is shown that regularity is preserved under choice, concatenation, and Kleene-closure. We show that this formalism is also useful in describing system performance measures such as completion time, reliability, etc., and present properties to aide their computation     

A local-motion-based probabilistic model for visual tracking

Color-based tracking is prone to failure in situations where visually similar targets are moving in a close proximity or occlude each other. To deal with the ambiguities in the visual information, we propose an additional color-independent visual model based on the target's local motion. This model is calculated from the optical flow induced by the target in consecutive images. By modifying a color-based particle filter to account for the target's local motion, the combined color/local-motion-based tracker is constructed. We compare the combined tracker to a purely color-based tracker on a challenging dataset from hand tracking, surveillance and sports. The experiments show that the proposed local-motion model largely resolves situations when the target is occluded by, or moves in front of, a visually similar object.     

Integrating integer programming and probabilistic deduction graphs for probabilistic reasoning

Optimal solutions of several variants of the probabilistic reasoning problem were found by a new technique that integrates integer programming and probabilistic deduction graphs (PDG). PDGs are extended from deduction graphs of the and-type via normal deduction graphs. The foregoing variants to be solved can involve multiple hypotheses and multiple evidences where the former is given and the latter is unknown and being found or vice versa. The relationship among these hypotheses and evidences with possible intermediaries is represented by a causal graph. The proposed method can handle a large causal graph of any type and find an optimal solution by invoking a linear integer programming package. In addition, formulating the reasoning problem to fit integer programming takes a polynomial time. H.-L. Li was visiting the Department of Computer Sciences, University of North Texas in 1988–1989. He is with the Institute of Information Management, National Chiao Tung University, Hsinchu, Taiwan, R.O.C.     

Information and probabilistic reasoning

In this paper, the relationship between information and reasoning is investigated and a parallel reasoning method is proposed based on information theory, in particular the principle of minimum cross entropy. Some technical issues, such as multiple uncertain evidence, complicated constraints, small directed cycles and decomposition of underlying networks, are discussed. Some simple examples are also given to compare the method proposed here with other methods.     

Structural and probabilistic knowledge for abductive reasoning

Different ways of representing probabilistic relationships among the attributes of a domain ar examined, and it is shown that the nature of domain relationships used in a representation affects the types of reasoning objectives that can be achieved. Two well-known formalisms for representing the probabilistic among attributes of a domain. These are the dependence tree formalism presented by C.K. Chow and C.N. Liu (1968) and the Bayesian networks methodology presented by J. Pearl (1986). An example is used to illustrate the nature of the relationships and the difference in the types of reasoning performed by these two representations. An abductive type of reasoning objective that requires use of the known qualitative relationships of the domain is demonstrated. A suitable way to represent such qualitative relationships along with the probabilistic knowledge is given, and how an explanation for a set of observed events may be constituted is discussed. An algorithm for learning the qualitative relationships from empirical data using an algorithm based on the minimization of conditional entropy is presented     

Modelling default and likelihood reasoning as probabilistic reasoning

This paper presents a probabilistic analysis of plausible reasoning about defaults and about likelihood. Likely and by default are in fact treated as duals in the same sense as possibility and necessity. To model these four forms probabilistically, a logicQDP and its quantitative counterpartDP are derived that allow qualitative and corresponding quantitative reasoning. Consistency and consequence results for subsets of the logics are given that require at most a quadratic number of satisfiability tests in the underlying prepositional logic. The quantitative logic shows how to track the propagation error inherent in these reasoning forms. The methodology and sound framework of the system highlights their approximate nature, the dualities, and the need for complementary reasoning about relevance.Much of this research was done while at the University of Technology, Sydney, Broadway, NSW, Australia, and some at the Turing Institute, 36 Nth. Hanover Str., Glasgow, Scotland.     

PRL: A probabilistic relational language

In this paper, we describe the syntax and semantics for a probabilistic relational language (PRL). PRL is a recasting of recent work in Probabilistic Relational Models (PRMs) into a logic programming framework. We show how to represent varying degrees of complexity in the semantics including attribute uncertainty, structural uncertainty and identity uncertainty. Our approach is similar in spirit to the work in Bayesian Logic Programs (BLPs), and Logical Bayesian Networks (LBNs). However, surprisingly, there are still some important differences in the resulting formalism; for example, we introduce a general notion of aggregates based on the PRM approaches. One of our contributions is that we show how to support richer forms of structural uncertainty in a probabilistic logical language than have been previously described. Our goal in this work is to present a unifying framework that supports all of the types of relational uncertainty yet is based on logic programming formalisms. We also believe that it facilitates understanding the relationship between the frame-based approaches and alternate logic programming approaches, and allows greater transfer of ideas between them. Editors: Hendrik Blockeel, David Jensen and Stefan Kramer An erratum to this article is available at .     

Web robot detection: A probabilistic reasoning approach

In this paper, we introduce a probabilistic modeling approach for addressing the problem of Web robot detection from Web-server access logs. More specifically, we construct a Bayesian network that classifies automatically access log sessions as being crawler- or human-induced, by combining various pieces of evidence proven to characterize crawler and human behavior. Our approach uses an adaptive-threshold technique to extract Web sessions from access logs. Then, we apply machine learning techniques to determine the parameters of the probabilistic model. The resulting classification is based on the maximum posterior probability of all classes given the available evidence. We apply our method to real Web-server logs and obtain results that demonstrate the robustness and effectiveness of probabilistic reasoning for crawler detection.     

Algebraic reasoning for probabilistic action systems and while-loops

Back and von Wright have developed algebraic laws for reasoning about loops in a total correctness framework using the refinement calculus. We extend their work to reasoning about probabilistic loops in the probabilistic refinement calculus. We apply our algebraic reasoning to derive transformation rules for probabilistic action systems and probabilistic while-loops. In particular we focus on developing data refinement rules for these two constructs. Our extension is interesting since some well known transformation rules that are applicable to standard programs are not applicable to probabilistic ones: we identify some of these important differences and we develop alternative rules where possible.     

A visual language compiler

The SIL-ICON compiler is a software system for the specification, interpretation, prototyping, and generation of icon-oriented systems. The system design of the SIL-ICON compiler is presented. The icon system G, the icon dictionary ID, the operator dictionary OD, and the extended task action grammar ETAG are described. An application example to design a text editor using the Heidelberg icon set is also presented in detail     

A probabilistic reasoning model: Formulation and control strategy

It has been recognized that past experiences of a decision maker often plays a pivotal role in solving new problem instances. Therefore, the ability to model human reasoning processes has become an important subject of research in recent years. In many applications, the reasoning process must deal with uncertainty inherent in the problem domain. This research addresses the issue of supporting the model formulation and data acquisition processes for situations that (i) operate under uncertain conditions, and (ii) utilize evidential information that is gathered in stages. A theoretical framework is presented for the probabilistic formulation of the reasoning process that incorporates past experiences. The model is validated by testing its performance on simulated data, and is shown to work well when a sufficiently large number of cases are available for estimating probabilities. The probabilistic reasoning system can revise beliefs in an intuitively appealing and theoretically sound manner when information is acquired in an incremental fashion. Two dynamic information gathering strategies are discussed for such a reasoning system, one using information theoretic techniques, and the other using decision theoretic techniques.     

A visual programming language for XML manipulation

XML data flow has reached beyond the world of computer science and has spread to other areas such as data communication, e-commerce and instant messaging. Therefore, manipulating this data by non-expert programmers is becoming imperative and has emerged two alternatives. On one hand, Mashups have emerged a few years ago, providing users with visual tools for web data manipulation but not necessarily XML specific. Mashups have been leaning towards functional composition but no formal definitions have yet been defined. On the other hand, visual languages for XML have been emerging since the standardization of XML, and mostly relying on querying XML data for extraction or structure transformations. These languages are mainly based on existing textual XML languages, they have limited expressiveness and do not provide non-expert programmers with means to manipulate XML data. In this paper, we define a generic visual language called XCDL based on Colored Petri Nets allowing non-expert programmers to compose manipulation operations. The XML manipulations range from simple data selection/projection to data modification (insertion, removal, obfuscation, etc.). The language is oriented to deal with XML data (XML documents and fragments), providing users with means to compose XML oriented operations. The language core syntax is presented here along with an implemented prototype based on it.     

A propositional probabilistic logic with discrete linear time for reasoning about evidence

The aim of the paper is to present a sound, strongly complete and decidable probabilistic temporal logic that can model reasoning about evidence. The formal system developed here is actually a solution of a problem proposed by Halpern and Pucella (J Artif Intell Res 26:1–34, 2006).     

A case based reasoning model for multilingual language generation in dialogues

The process of Natural Language Generation for a Conversational Agent translates some semantic language to its surface form expressed in natural language. In this paper, we are going to show a Case Based Reasoning technique which is easily extensible and adaptable to multiple domains and languages, that generates coherent phrases and produces a natural outcome in the context of a Conversational Agent that maintains a dialogue with the user.     

Using probabilistic reasoning over time to self-recognize

Using the probabilistic methods outlined in this paper, a robot can learn to recognize its own motor-controlled body parts, or their mirror reflections, without prior knowledge of their appearance. For each item in its visual field, the robot calculates the likelihoods of each of three dynamic Bayesian models, corresponding to the categories of “self”, “animate other”, or “inanimate”. Each model fully incorporates the object’s entire motion history and the robot’s whole motor history in constant update time, via the forward algorithm. The parameters for each model are learned in an unsupervised fashion as the robot experiments with its arm over a period of four minutes. The robot demonstrated robust recognition of its mirror image, while classifying the nearby experimenter as “animate other”, across 20 experiments. Adversarial experiments, in which a subject mirrored the robot’s motion showed that as long as the robot had seen the subject move for as little as 5 s before mirroring, the evidence was “remembered” across a full minute of mimicry.     

A visual language compiler for information retrieval by visualreasoning

When a database increases in size, retrieving the data becomes a major problem. An approach based on data visualization and visual reasoning is described. The main idea is to transform the data objects and present sample data objects in a visual space. The user can use a visual language to incrementally formulate the information retrieval request in the visual space. A prototype system is described with the following features: (1) it is built on top of the SIL-ICON visual language compiler and therefore can be customized for different application domains; (2) it supports a fuzzy icon grammar to define reasonable visual sentences; (3) it incorporates a semantic model of the database for fuzzy visual query translation; and (4) it incorporates a VisualNet which stores the knowledge learned by the system in its interaction with the user so that the VisualReasoner can adapt its behavior     

A visual language for modeling and executing traceability queries

Current software and systems engineering tools provide only basic trace features, and as a result users are often compelled to construct non-trivial traceability queries using generic query languages such as SQL. In this paper, we present an alternative approach which defines traceability strategies for a project using UML class diagrams and then constructs trace queries as constraints upon subsets of the model. The visual trace modeling language (VTML) allows users to model a broad range of trace queries while hiding underlying technical details and data structures. The viability and expressiveness of VTML for use in a real project are demonstrated through modeling a broadly representative set of queries for a web-based health-care system. It is then evaluated through an experiment with human users to assess the readability and writability of VTML queries in comparison to generic SQL queries. We found that users read and constructed traceability queries considerably faster using VTML than using SQL. Furthermore, visually constructed traceability queries were substantially more correct compared to the same queries constructed with SQL.     

POSAML: A visual modeling language for middleware provisioning

Next generation distributed applications are often hosted on heterogeneous platforms including different kinds of middleware. Due to the applications’ growing functional complexity and their multiple quality of service (QoS) requirements, system developers are increasingly facing a substantial number of middleware provisioning challenges, which include configuring, optimizing and validating the middleware platforms for QoS properties. Traditional techniques for middleware provisioning tend to use non-intuitive, low-level and technology-specific approaches, which are tedious, error prone, and non-reusable across different technologies. Quite often the middleware provisioning activities are carried out by different actors without much interaction among them, which results in an iterative trial-and-error process to provisioning. Higher level abstractions, particularly those that use visual models, are effective in addressing these challenges. This paper describes the design of a visual modeling language called POSAML (pattern-oriented software architecture modeling language) and associated tools that provide an intuitive, higher level and unified framework for provisioning middleware platforms. POSAML provides visual modeling capabilities for middleware-independent configurations and optimizations while enabling automated middleware-specific validation of system QoS properties.