Abstract: Methods and systems for dynamically updating machine learning models that provide conversational responses through the use of a configuration file that defines modifications and changes to the machine learning model are disclosed. For example, the configuration file may be used to define an expected behavior and required attributes for instituting modifications and changes (e.g., via a mutation algorithm) to the machine learning model.

Abstract: Implementations of various methods and systems to transform tutoring units with two waypoints or a destination waypoint or a series sequence of waypoints into objects which have associated price-time priority queues for transformed tutoring units. The present disclosed invention relates to combining the concepts of objected oriented programming, market price queues, tutoring, navigation systems and social networking and transportation as a fungible asset class or tutoring linked to transportation as an open market.

Abstract: A data recorder stores endpoint activity on an ongoing basis as sequences of events that causally relate computer objects such as processes and files. When a security event is detected, an event graph may be generated based on these causal relationships among the computing objects. For a root cause analysis, the event graph may be traversed in a reverse order from the point of an identified security event (e.g., a malware detection event) to preceding computing objects, while applying one or more cause identification rules to identify a root cause of the security event. Once a root cause is identified, the event graph may be traversed forward from the root cause to identify other computing objects that are potentially compromised by the root cause.

Abstract: A method includes receiving a representation of a spoken utterance, processing the representation of the spoken utterance to identify, from a number of candidate domains, a request and a serving domain, and routing the request to a personal assistant based on the request and the serving domain. Identification of the serving domain is based on one or more of a contextual state, a behavior profile of a speaker of the utterance, and a semantic content of the utterance.

Abstract: Methods and systems for dynamically updating machine learning models that provide conversational responses through the use of a configuration file that defines modifications and changes to the machine learning model are disclosed. For example, the configuration file may be used to define an expected behavior and required attributes for instituting modifications and changes (e.g., via a mutation algorithm) to the machine learning model.

Abstract: At least one of the embodiments described herein relate generally to a method of obtaining metadata for content stored in a first repository. The method may be performed at a second repository, and may include the acts of: identifying a content object stored in the first repository, the content object including learning content usable in an electronic educational system to provide electronic learning; identifying metadata for the content object stored in the first repository, the metadata associated with the learning content of the content object; retrieving the metadata associated with the learning content from the first repository; and storing a harvested content object corresponding to the content object. The harvested content object may includes the metadata associated with the learning content of the content object stored in the first repository.

Abstract: Generally, the present disclosure is directed to managing shared resources in a multi-modality medical system. A multi-modality medical system acquires, stores, processes, and displays data associated with a plurality of different medical modalities. Although different, independent modules within the medical system handle different modality workflows, such modules rely on common resources in the system. The method and systems described herein coordinate usage of the common resources, such as a display viewport, among the independent modality modules. For example, a token-based, locking scheme is utilized to exclusively assign a shared resource to a single modality component. This locking scheme prevents, for example, resource deadlocks from occurring during a patient procedure, thus enhancing patient safety.

Abstract: Methods and systems are disclosed for structuring and using information pertinent to in vivo biomarkers, specifically quantitative imaging biomarkers, using semantic web technology for personalized medicine and discovery science. It supports the development and application of statistical evidence at a level of granularity and sophistication more closely tied to the complexity of the disease itself and its underlying biology, including technology linking multiple biological scales, than has previously been eedisclosed. It provides data and computational services to analyze quantitative imaging and non-imaging data, coupled with multi-scale modeling to elucidate pre-symptomatic and clinical disease processes. It may be used to assess technical or analytical performance for its own sake and/or to further annotate the quantitative analysis.

Abstract: According to an aspect of an embodiment, a computer system including at least one computer is configured to generate, specification concept graphs of nodes spec1, spec2, . . . , specm including concepts node and relation nodes according to at least one of a plurality of digitized data from user input from a plurality of computerized data sources d1, d2, . . . , dl forming a first set of evidences U; generate concept graphs of nodes c?1, c?2, . . . , c?n including concept nodes and relation nodes for corresponding obtained plurality of IKs ?1, ?2, . . . , ?n forming a second set of evidences U; select a subset of concept graphs of nodes c?i1, c?i2, . . . , c?ih from c?1, c?2, . . . , c?n according to a computable measure of any one or combinations of consistency, inconsistency or priority threshold between c?j in c?1, c?2, . . . , c?n to specification concept graph speck in spec1, spec2, . . . , specm. Generate knowledge fragments for corresponding obtained subset of concept graphs c?i1, c?i2, . . . c?ih.

Abstract: The present subject matter relates to entity resolution, and in particular, relates to providing an entity resolution from documents. The method comprises obtaining the plurality of documents from at least one data source. The plurality of documents is blocked into at least one bucket based on textual similarity and inter-document references among the plurality of documents. Further, within each bucket, a merged document for each entity may be created based on an iterative match-merge technique. The iterative match-merge technique identifies, from the plurality of documents, at least one matching pair of documents and merges the at least one matching pair of documents to create the merged document for each entity. The merged documents may be merged to generate a resolved entity-document for each entity based on a graph clustering technique.

Abstract: Generally, the present disclosure is directed to managing shared resources in a multi-modality medical system. A multi-modality medical system acquires, stores, processes, and displays data associated with a plurality of different medical modalities. Although different, independent modules within the medical system handle different modality workflows, such modules rely on common resources in the system. The method and systems described herein coordinate usage of the common resources, such as a display viewport, among the independent modality modules. For example, a token-based, locking scheme is utilized to exclusively assign a shared resource to a single modality component. This locking scheme prevents, for example, resource deadlocks from occurring during a patient procedure, thus enhancing patient safety.

Abstract: An event processing system includes a multi-agent based system, which includes a core engine configured to define and deploy a plurality of agents configured to perform a first set of programmable tasks defined by one or more users. The first set of tasks operates with real time data. The multi-agent based system also includes a monitoring engine configured to monitor a lifecycle of the agents, communication amongst the agents and processing time of the tasks. The multi-agent based system further includes a computing engine coupled to the core engine and configured to execute the first set of tasks. The event processing system includes a batch processing system configured to enable deployment of a second set of programmable tasks that operates with non-real time data and a studio coupled to the multi-agent based system and configured to enable users to manage the multi-agent based system and the batch processing system.

Abstract: A method and system for creating a histogram of oriented occurrences (HO2) is disclosed. A plurality of entities in at least one image are detected and tracked. One of the plurality of entities is designated as a reference entity. A local 2-dimensional ground plane coordinate system centered on and oriented with respect to the reference entity is defined. The 2-dimensional ground plane is partitioned into a plurality of non-overlapping bins, the bins forming a histogram, a bin tracking a number of occurrences of an entity class. An occurrence of at least one other entity of the plurality of entities located in the at least one image may be associated with one of the plurality of non-overlapping bins. A number of occurrences of entities of at least one entity class in at least one bin may be into a vector to define an HO2 feature.

Abstract: Methods, systems, and computer program products for automatically triggering actions on a user device based on biometrics of nearby individuals are provided herein. A method includes capturing, via one or more sensors resident on a first computing device, one or more items of biometric information from one or more individuals located within a given proximity of the first computing device; determining a degree of proximity of the one or more individuals to the first computing device; transmitting, to a second computing device, (i) the one or more captured items of biometric information from the one or more individuals and (ii) the determined degree of proximity of the one or more individuals to the first computing device; and automatically executing one or more actions on the first computing device based on an instruction provided by the second computing device in response to said transmitting.

Abstract: An adaptable graphical user interface is provided. The interface may include a setup region to display a group of available solvers to a user and to display parameters for at least one of the group of solvers to the user. The interface may include an options region to display a first group of active options to a user without requiring a user input for the first group of active options, where the first group of active options is determined based on a selected one of the group of solvers. The options region may further display a second group of active options to the user when another one of the solvers is selected by the user, where the second group of active options differs from the first group of active options.

Abstract: Methods and apparatus for instance host configuration are disclosed. A system includes a plurality of instance hosts configurable for resource instances of a network-accessible service, and control servers to manage remote configuration of the instance hosts. In response to an instance configuration request from a client, a selected control server transmits, to a selected instance host, a sequence of one or more commands. The selected instance host instantiates a remote command executor. The remote command executor initiates configuration operations corresponding to the command sequence, and terminates. The selected control server provides a response to the instance configuration request, based at least in part on results of the operations initiated by the executor.

Abstract: A system and method for routing and managing documents based on document content comprises obtain a document, determine a classification for the document based on the document content, determine a storage location for the document based on the document classification, determine whether the document is stored in the determined storage location, when the document is stored in the determined storage location, update the document in the determined storage location, when the document is not stored in the determined storage location, determine whether the document is stored in another storage location, when the document is stored in another storage location, add the document in the determined storage location and delete the document from the other storage location, and when the document is not stored in the other storage location, add the document to the determined storage location.

Abstract: A method for merging information of high semantic level representing complex situations including several objects originating from several sensors ci, said information possibly being heterogeneous, said method including acquiring the various items of information arising from said sensors in raw form and transforming them so as to cast them into the form of conceptual graphs, a conceptual graph representing several concepts and the relations which exist between them, and being composed of entity nodes and relation nodes, with E the set of concept nodes defined on a support S, G1 and G2 two conceptual graphs defined on S, wherein the method determines a merging strategy denoted strategymerge as follows: strategymerge=fmerge?fcomp:E×E?E?{E×E} and said merging strategy is applied to the various items of information taking the form of graphs.

Abstract: Apparatus, systems, and methods that operate to assist in resolving both expected and unexpected events that occur in the course of business operations are disclosed. Activities may include detecting the occurrence of an alert event, determining whether the alert event is an expected event or an unexpected event, presenting a resolution sequence for the expected event, and soliciting a new event resolution path for the unexpected event. Further activities may include determining an alert event is an unexpected event, displaying an alert message associated with the unexpected event, and soliciting recommendations to form a new event resolution path to be presented upon determining a new event has occurred that is similar to the alert event. Additional apparatus, systems, and methods are disclosed.

Abstract: Systems and methods provide a mechanism to create and traverse inter-document links involving embedded documents. One aspect of the systems and methods includes creating and traversing inter-document links to and from documents that are embedded in a host document. A further aspect of the systems and methods includes creating and traversing inter-document links to an from documents that may be embedded at more than one level in an embedded document hierarchy. A still further aspect of the systems and methods includes creating and traversing inter-document links from a first document to an embedded document in a second document.

Abstract: A method of compiling causal rules into continuations for use in root cause analysis of a system comprising a plurality of inter-related elements, comprising defining observable events occurring on system elements; defining at least one of a cause and a result of each of the events; defining causal rules, each rule describing a causal relationship between an event and one of its cause and its result; and compiling the causal relationships as continuations in a continuation passing style (CPS) for use in analyzing the root cause of subsequent observed events symptomatic of at least one problem on the system.

Abstract: Embodiments of the invention disclose a system and a method for determining a differentially private aggregate classifier for a set of databases, wherein each database in the set of databases is associated with a classifier and a noise value, wherein the classifier and the noise value are determined locally for each database, such that a combination of the classifier and the noise value ensure a differential data privacy of the database, and wherein the differentially private aggregate classifier preserves the differential data privacy of each database. The differentially private aggregate classifier is a combination of the classifiers of the set of databases modified with the noise value corresponding to a smallest database in the set of databases.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for distributed nearest-neighbor search for image retrieval are disclosed. An example distributed image retrieval system includes a root server and a plurality of leaf servers. The root server controls the clustering of images in the image corpus, and determines the assignment of image clusters to a collection of leaf servers. Each leaf server is independently configured to perform a two-stage nearest-neighbor search in a locality-sensitive hash space for a received query image within the leaf server's assigned images clusters. Thus, the distributed image retrieval system is modular and amendable to tuning, modifications, duplication, and replacement on a per-server basis. In addition, the design of the image retrieval system allows flexible load balancing among the leaf servers.

Abstract: Systems and methods are provided for integrating educational software. In one implementation, a first method includes providing on a first server an integrated learning management system adapted to exchange education data and materials via a connector interface, providing on the first server a first component which responds to requests made by the integrated system via the connector interface to exchange education data and materials with a first source learning management system, and exchanging education data and materials between the integrated system and the first system via the first component by use of the connector interface.

Abstract: A method of performing root cause analysis for use in a system comprising a plurality of inter-related elements, wherein at least some of the elements experience one or more abnormal conditions, comprising defining one or more conditions for more than one element symptomatic of abnormal operation of the element; defining one or more causal relationships between the conditions and results on one or more related elements; compiling the conditions and causal relationships of each element for which conditions and relationships have been defined, as at least one continuation in a continuation passing style (CPS); receiving one or more observed events symptomatic of abnormal operation of at least one element of the system; processing the received events using the conditions and the continuations; concluding at least one root cause of the received events consistent with the received events; and outputting the root cause.

Abstract: Systems and methods for providing an integrated HMI application for monitoring and interacting with both batch and non-batch processes in a process plant are disclosed. A plurality of independent stand-alone software objects defining various batch process interface views are embedded within a non-batch process control interface application. A blackboard service is provided for storing batch control data used by the various stand alone software objects. The blackboard service may be adapted to communicate with a batch control server to receive batch control data for populating the various batch interface views with data relating to various batch processes being carried out in the process plant and to send instructions for controlling the various batches input by users via the various batch interface views.

Abstract: A system and method is provided to facilitate communication and collaboration by considering the timing of a user's activities on one or more clients via accessing, from a centralized server, information about the user's client-server interactions. The systems and methods can harness existing protocols and data exchange used in legacy client-server applications for email, making available to one or more client-side message routing applications, information about a user's interactions with email across multiple clients. Applications include considering the time since the last client-server interaction to guide decisions about if, when, and how to route messages so as to limit the mobile relay of information a user has already seen, providing information to colleagues about a user's current or past “inbox presence,” and forecasting the time until a user will have access to a device or communication channel.

Abstract: Systems and methods are provided for integrating educational software. In one implementation, a first server receives an identifier of a second server that provides at least one source educational course. A second server receives metadata for the at least one source educational course and stores the metadata.

Abstract: The invention relates according to a first aspect to a method of driving a telecommunications network comprising equipment responsible for carrying out network control tasks, each item of equipment comprising a knowledge base intended for storing, in the form of elements dubbed knowledge, contextual information required in order for the equipment to carry out the control tasks for which it is responsible, the method being characterized in that: a logical neighbourhood is defined, consisting of network equipment—intended to cooperate in order to carry out one and the same control task; the knowledge stored in the various knowledge bases is mutualized in the logical neighbourhood, by implementing for each item of equipment of the logical neighbourhood a cooperation of said item of equipment with the other items of equipment of the logical neighbourhood; in each item of equipment of the logical neighbourhood, the same control task is carried out by feeding it with the mutualized knowledge stored in the knowledge

Abstract: The safety in robotic operations is enhanced and the floor space in a factory or the like is effectively utilized. A virtual safety barrier 50 including the trajectory of movement of a work or tool 7 mounted on a wrist 5 of a robot 1 in operation is defined in a memory. At least two three-dimensional spatial regions S (S1 to S3) including a part of the robot including the work or tool are defined. Predicted positions of the defined three-dimensional spatial regions obtained by trajectory calculations are matched with the virtual safety barrier 50, and if the predicted position of any one of the defined three-dimensional spatial regions based on trajectory calculations is included in the virtual safety barrier 50, a control is effected to stop the movement of the robot arms 3 and 4.

Abstract: A system, apparatus and method are provided that enable the receipt of answers to questions from users and to make those answers persistent within a generalized database schema. A set of one or more middleware entities and components are provided to process the user's answers that are submitted to the system. The middleware entities differentiate one user from another user by use of a session. Different sets of questions are grouped into encounters, and the answers to the questions for a particular encounter are given a unique identifier. The unique identifier can be used to identify the user and/or the particular encounter. The answers to the questions can be retrieved and viewed in numerous ways, such as by user, by encounter, by question, by question type, by answer, by answer type, etc. The selection of database schema and the structure of the middleware enables the system to handle any answer to any question without requiring the restructuring of the database or database schema.

Abstract: A quality improvement system, which automatically performs engineering analysis and problem coping to improve the quality of semiconductor products. The quality improvement system is connected to a plurality of external databases, which store semiconductor product quality information acquired in a plurality of manufacturing processes, and a client server, which is operated by an engineer. The quality improvement system receives quality information from the external databases, receives engineer comments from the client server and associates the quality information and comments and stores them in a knowledge database.

Abstract: Systems and methods are provided for integrating educational software. In one implementation, a first server receives an identifier of a second server that provides at least one source educational course. A second server receives metadata for the at least one source educational course and stores the metadata.

Abstract: A system is provided for pro-actively suggesting communication features to users, comprising a tuple space for facilitating collaboration among software agents, a plurality of device agents for controlling operation of associated communication devices for respective ones of the users, and a plurality of user agents representing a plurality of users, each of the user agents (i) facilitating creation, by a user desirous of communicating, of groups of users to be communicated with, (ii) poking tuples to the tuple space indicative of each user's availability for communication; (iii) peeking anti-tuples to the tuple space for eliciting communication availability of respective ones of the users in the groups of users to be communicated with and in response causing associated device agents to display via respective ones of the devices the aforementioned availability to the user desirous of communicating, and to effect communication between the user desirous of communicating and a selected one of the respective users

Abstract: A computer-implemented method and system for implementing a software agent control architecture. The method includes the step of generating a plurality of agents, wherein the agents are respectively configured to implement a rule-based behaviour. Respective rule sets for each of the agents are accessed, wherein the rule sets are configured for processing using respective rule engines of each of the agents. Respective incoming messages are received and delivered to the agents. The rule-based behaviour for each of the agents is implemented by processing the incoming messages using the rule engines.

Abstract: An exemplary embodiment of the present invention is directed to a system, method and computer program product for providing an object recognition blackboard system architecture. The system for recognizing objects in content can include: a blackboard comprising a plurality of experts, and data comprising original input data and data created by processing of any of the plurality of experts, and a controller operative to control the experts; a belief model, coupled to the controller, comprising a set of beliefs and probabilities associated with each belief of the set of beliefs; a belief network, coupled to the controller; and a relations subsystem, coupled to the controller.

Abstract: A method of detecting feature interaction conflicts between agents in response to events in a multi-agent system comprises posting said events as tuples and event requests as anti-tuples from said agents in said multi-agent system, receiving said events and said event requests in a tuple space, generating responses to each of said agents for said events which match said event requests of said agents, wherein feature interaction conflict is detected when more than one of said agents are to exert control over an event.

Abstract: An embedded device for playing media files is capable of generating a play list of media files based on input speech from a user. It includes an indexer generating a plurality of speech recognition grammars. According to one aspect of the invention, the indexer generates speech recognition grammars based on contents of a media file header of the media file. According to another aspect of the invention, the indexer generates speech recognition grammars based on categories in a file path for retrieving the media file to a user location. When a speech recognizer receives an input speech from a user while in a selection mode, a media file selector compares the input speech received while in the selection mode to the plurality of speech recognition grammars, thereby selecting the media file.

Abstract: An online monitor that can be permanently attached to a device to be monitored continuously monitors a set of analog signals and initiates data capture over a window of time when a user programmable set of conditions is satisfied. The online monitor includes a digital signal processing unit, a modular, interchangeable, analog signal conditioning base unit that can be tailored to the specific requirements of the process to be monitored and a modular, interchangeable, communication interface unit. The interface unit permits the digital signal processing unit to exchange data with external equipment such as network computers via a number of industry standard communication fieldbus protocols. The online monitor provides the capability to define the trigger condition under which data capture is initiated by comparing a user defined signal to a function of the instantaneous value of another signal or constant.

Abstract: A system and method to interact with networked objects, via a computer using utterances, speech processing and natural language processing. A Data Definition File relates networked objects and a speech processor. The Data Definition File encompasses a memory structure relating the networked objects, including grammar files and a natural language processor. The speech processor searches a first grammar file for a matching phrase for the utterance, and to search a second grammar file for the matching phrase if the matching phrase is not found in the first grammar file. The system also includes a natural language processor to search a database for a matching entry for the matching phrase; and an application interface to perform an action associated with the matching entry if the matching entry is found in the database. The system utilizes context-specific grammars, thereby enhancing speech recognition and natural language processing efficiency.

Abstract: In a method for implementation of a fault diagnostic system having a number of diagnostic modules and in an in-vehicle fault diagnostic system, a second diagnostic module whose diagnostic result depends on the result of the fault diagnosis of at least one first diagnostic module begins its diagnostic cycle without waiting for the diagnostic result of the first diagnostic module. The second diagnostic module writes its diagnostic result into a secondary fault memory. When the first diagnostic module has ended its diagnostic cycle without finding a fault, the diagnostic result of the second diagnostic module is transferred from the secondary fault memory into a primary fault memory.

Abstract: An architecture for a computer system for problem solving and tutoring includes multiple domain dependent agents, each having a knowledge base, multiple domain independent agents and dedicated blackboards assigned to each agent. The agents communicate with their dedicated blackboards via a transmission control protocol/internet protocol (TCP/IP) links and messages are moved between the blackboards by a blackboard agent. The domain independent agents include a control agent that passes a token between the agents. An agent may function only when it has the token. The domain independent agents also include a user interface agent, a database agent and a tutoring agent. Training/testing data repository and student databases are also present. The latter stores information regarding student actions during testing or tutoring sessions. The architecture may be employed on multiple machines to permit geographically diverse users to simultaneously role-play.

Abstract: An exemplary embodiment of the present invention is directed to a system, method and computer program product for providing an object recognition blackboard system architecture. The system for recognizing objects in content can include: a blackboard comprising a plurality of experts, and data comprising original input data and data created by processing of any of the plurality of experts, and a controller operative to control the experts; a belief model, coupled to the controller, comprising a set of beliefs and probabilities associated with each belief of the set of beliefs; a belief network, coupled to the controller; and a relations subsystem, coupled to the controller.

Abstract: An intelligent agent workbench is disclosed for developing a computer-based intelligent agent that can be inserted between a system and an individual performing a pre-defined function with the system and/or that can supplant such function performed by such individual. In the workbench, an agent author allows a workbench user to create and modify an intelligent agent in a graphical representation. The workbench also has an execution engine for executing a non-graphical representation of the agent both within the workbench and outside the workbench as a stand-alone agent, and an interpreter for automatically translating between the non-graphical and graphical representations. The agent has an instance structure representing a current problem instance, perception structures, task performance structures, and a priority structure.

Abstract: A method for automatically interpreting an electronic message, including the steps of (a) receiving the electronic message from a source; (b) interpreting the electronic message using a rule base and case base knowledge engine; and (c) classifying the electronic message as at least one of (i) being able to be responded to automatically; and (ii) requiring assistance from a human operator. The method for automatically interpreting an electronic message may also include the step of retrieving one or more predetermined responses corresponding to the interpretation of the electronic message from a repository for automatic delivery to the source.

Abstract: A system for building collaborative software agents is provided with a set of editors for capturing data for installation in the individual agents. The collaborative software agents will normally form a community, including some standard agents, provided by the system, and will collaborate to provide functionality in a domain selected by the user. Each collaborative software agent built by the system is provided with co-ordination policies, selected by the user, and represented by a co-ordination graph. A single collaborative software agent can be provided with more than one collaborative policy and is capable of running more than one collaborative policy simultaneously with different agents of the system. An exception handler flags an exception during use of the collaborative agents in the relevant domain when the value of a variable for an agent conflicts with a relevant constraint.

Abstract: A method for the selection of hypotheses for modeling physical phenomena, includes detecting if selected features are present by analyzing actual sensed data and parameter values of an initial physical phenomena model; comparing feature estimating hypotheses to the actual data for determining a belief probability assignment value (bpa) for each of the hypotheses which indicates the likelihood that the selected features exist in the actual data and the likelihood that such selected features cannot accurately be determined as existing due to the presence of noise; selecting a set of the hypotheses most accurately modeling the physical phenomena based on the bpa of each selected hypotheses meeting a predetermined criteria; generating evidential support values and lack of evidential support values for subsets of the set having non-zero subset bpa's; ranking the subsets having non-zero subset bpa's in order of decreasing subset bpa; unioning subsets of the power set for forming unioned subsets and determ

Abstract: A computer software architecture for an embedded computer system. The architecture includes a hierarchy of software object classes. One classification includes a common information blackboard object. Data is written to the blackboard object by processes in a protected manner, and is otherwise globally readable by all processes. A run-time executive is provided to schedule and coordinate processes. Processes register with the run-time executive at start-up. One process can know the existence and generation of data by another process. The architecture is layered in increasing levels of system abstraction. In one embodiment, the embedded system is an airborne fuel gauging subsystem.

Abstract: A system which observes the world through a video camera and/or other sensors, automatically learns a probabilistic model of normative behavior through the use of a Hidden Markov Model, and uses that model to infer the kind of activity currently under view and detect unusual behavior. The use of hidden Markov models is made possible by entropic training of the model with an &thgr;&thgr; entropic estimator that folds structure learning into the parameter estimation process to remove parameters from the Hidden Markov Model which have little information content, thus to permit real time robust unusual behavior detection. In one embodiment, the system consists of three components: image analysis; model learning; and signal analysis. In image analysis, each frame of video is reduced to a vector of numbers which describe motion of objects in front of the camera, with a sequence of such vectors, one for each frame of video, establishing the “signal.

Abstract: This invention relates to a method of configuring a set of objects in a computer, each object having at least one possible value, each value being determined or undetermined, and at least one of said object values being accessible to a user for assigning at least one value to be determined or undetermined, said values being constrained by a rule base defining a number of relationships between the values. The undetermined object values are searched in order to find at least one first subset of values, said first subset and a subset of determined values defining at least one first possible configuration of object values satisfying the rule base if said first subset exists, said search being initiated when at least one value of an object is changed or said search being initiated upon a user request.