Abstract: Methods and systems for interpretable user behavior profiling in off-street parking applications. To render user profiles easy to interpret by decision makers, the semi-automatic discovery and tagging of user profiles can be implemented. Transaction data from one or more (and geographically close) off-street parking installations can be implemented. An analysis of spatio-temporal behavioral patterns can be implemented based on representation of any parking episode by a set of heterogeneous features, the use of clustering methods for automatic pattern discovery, an assessment of obtained clusters, semi-automatic identification/tagging of space-temporal patterns, and a user-friendly interpretation of obtained patterns.

Abstract: A multi-task learning system and method for predicting travel demand on an associated transportation network are provided. Observations corresponding to the associated transportation network are collected and a set of time series corresponding to travel demand are generated. Clusters of time series are then formed and for each cluster, multi-task learning is applied to generate a prediction model. Travel demand on a selected segment of the associated transportation network corresponding to at least one of the set of time series is then predicted in accordance with the generated prediction model.

Abstract: A method and system are disclosed for re-ranking trips from a journey planner using real traveler preferences. A trip request is received that includes an origin, a destination and a departure time. An associated journey planner retrieves a list of candidate trips that correspond to the request. A ranking function, ascertained from actual trips that match the trip request and from which are determined real-world traveler preferences, is applied to the list of candidate trips output by the journey planner, thereby re-ranking the list of candidate trips to reflect real-world traveler's experiences.

Abstract: A classification system includes memory which stores, for each of a set of classes, a classifier model for assigning a class probability to a test sample from a target domain. The classifier model has been learned with training samples from the target domain and from at least one source domain. Each classifier model models the respective class as a mixture of components, the component mixture including a component for each source domain and a component for the target domain. Each component is a function of a distance between the test sample and a domain-specific class representation which is derived from the training samples of the respective domain that are labeled with the class, each of the components in the mixture being weighted by a respective mixture weight. Instructions, implemented by a processor, are provided for labeling the test sample based on the class probabilities assigned by the classifier models.

Abstract: In camera-based object labeling, boost classifier ƒT(x)=?r=1M?rhr(x) is trained to classify an image represented by feature vector x using a target domain training set DT of labeled feature vectors representing images acquired by the same camera and a plurality of source domain training sets DS1, . . . , DSN acquired by other cameras. The training applies an adaptive boosting (AdaBoost) algorithm to generate base classifiers hr(x) and weights ?r. The rth iteration of the AdaBoost algorithm trains candidate base classifiers hrk(x) each trained on a training set DT?DSk, and selects hr(x) from previously trained candidate base classifiers. The target domain training set DT may be expanded based on a prior estimate of the labels distribution for the target domain. The object labeling system may be a vehicle identification system, a machine vision article inspection system, or so forth.

Abstract: A system and method for classifying vehicles from laser scan data by receiving laser scan data corresponding to multiple vehicles from a laser scanner; extracting vehicle shapes corresponding to the multiple vehicles based on the laser scan data; aligning the vehicle shapes; and generating vehicle profiles based on the aligned vehicle shapes. The system and method can further include aligning the vehicle shapes using sequence kernels, such as global alignment kernels, and constraining the sequence kernels based on determined weights.

Abstract: A method and system is disclosed for tagging a latent object with selected tag recommendations, including a set of content objects wherein each object is characterized by an associated set of content features. An annotation relationship is determined between the features and a pre-determined tag for the each object, the relationship being defined by a graph construction representative of an affinity relationship between each pre-selected tag and content object to a selected query. A plurality of the annotation relationships are ranked based upon a relevance of the preselected tags to the content features in response to a new query for assigning a new tag to the each object, so that a suggested tag is made from the ranking whereby the suggested tag is determined as a most likely tag for annotating the content object.

Abstract: A multi-task learning system and method for predicting travel demand on an associated transportation network are provided. Observations corresponding to the associated transportation network are collected and a set of time series corresponding to travel demand are generated. Clusters of time series are then formed and for each cluster, multi-task learning is applied to generate a prediction model. Travel demand on a selected segment of the associated transportation network corresponding to at least one of the set of time series is then predicted in accordance with the generated prediction model.

Abstract: In demand prediction, a history of demand for a resource is modeled to generate a baseline model of the demand, and demand for the resource at a prediction time is predicted by evaluating a regression function of depth k operating on an input data set including at least the demand for the resource at the prediction time output by the baseline model and measured demand for the resource measured at k times prior to the prediction time. The resource may be off-street parking, and the input data set may further include weather data. The regression function may comprise a support vector regression (SVR) function that is trained on the history of demand for the resource. The baseline model suitably comprises a Fourier model of the history of demand for the resource.

Abstract: A multi-task machine learning component learns a set of tasks comprising two or more different tasks based on a set of examples. The examples are represented by features of a set of features. The multi-task machine learning component comprises a digital processing device configured to learn an ensemble of base rules wherein each base rule is learned for a sub-set of the set of features and comprises a multi-task decision tree (MT-DT) having nodes comprising decision rules for tasks of the set of tasks. An inference component comprises a digital processing device configured to predict a result for at least one task of the set of tasks for an input item represented by features of the set of features using the learned ensemble of base rules.

Abstract: Multi-label classification is performed by (i) applying a set of trained base classifiers to an object to generate base classifier label prediction sets comprising subsets of a set of labels; (ii) constructing a set of second level features including at least one second level feature defined by a predetermined combination of two or more of the base classifier label prediction sets; and (iii) applying a second level classifier to label the object with a set of one or more labels comprising a subset of the set of labels, labeling being based on the set of second level features. The multi-label classifier is trained by: (iv) applying operations (i) and (ii) to labeled training objects of a set of labeled training objects to generate training metadata comprising sets of second level features for the labeled training objects; and (v) training the second level classifier using the training metadata.

Abstract: Methods and systems for matching real trips to schedules in a public transportation system. Inputs can be reduced to a two-dimensional sequence alignment of data indicative of a temporal series of arrival and departure timestamps. A dynamic programming solution is applied to the two-dimensional sequence alignment of the data. Then, symmetric and asymmetric cases are analyzed with respect to the two-dimensional sequence alignment of the data to thereby match real trip data to schedule data in the public transportation system based on the temporal series of the arrival and departure timestamps.

Abstract: A method and system is disclosed for tagging a latent object with selected tag recommendations, including a set of content objects wherein each object is characterized by an associated set of content features. An annotation relationship is determined between the features and a pre-determined tag for the each object, the relationship being defined by a graph construction representative of an affinity relationship between each pre-selected tag and content object to a selected query. A plurality of the annotation relationships are ranked based upon a relevance of the preselected tags to the content features in response to a new query for assigning a new tag to the each object, so that a suggested tag is made from the ranking whereby the suggested tag is determined as a most likely tag for annotating the content object.

Abstract: A multi-relational data set is represented by a probabilistic multi-relational data model in which each entity of the multi-relational data set is represented by a D-dimensional latent feature vector. The probabilistic multi-relational data model is trained using a collection of observations of relations between entities of the multi-relational data set. The collection of observations includes observations of at least two different relation types. A prediction is generated for an observation of a relation between two or more entities of the multi-relational data set based on a dot product of the optimized D-dimensional latent feature vectors representing the two or more entities. The training may comprise optimizing the D-dimensional latent feature vectors to maximize likelihood of the collection of observations, for example by Bayesian inference performed using Gibbs sampling.

Abstract: A method and system are disclosed for trip planning using crowdsourcing. Validation information from automatic ticketing validation systems is collected and used to generate validation sequences, which include an origin, destination, and boarding and alighting timestamps. A path is defined from the validation sequence as a sequence of origins and destinations on a transportation network. The frequency of the path occurring for all travelers on the network is determined, along with the duration of travel time on the path. An expected transfer time between pairs of stations on the network is calculated from the duration, the pairs of stations corresponding to an origin and a destination in the sequence. One or more paths between a pair of stations corresponding to a selected origin and destination are identified and a trip plan is generated using the identified paths which have the least determined transfer time and the highest frequency of occurrences.

Abstract: A document annotation system includes a graphical user interface used by an annotator to annotate documents. An active learning component trains an annotation model and proposes annotations to documents based on the annotation model. A request handler conveys annotation requests from the graphical user interface to the active learning component, conveys proposed annotations from the active learning component to the graphical user interface, and selectably conveys evaluation requests from the graphical user interface to a domain expert. During annotation, at least some low probability proposed annotations are presented to the annotator by the graphical user interface. The presented low probability proposed annotations enhance training of the annotation model by the active learning component.

Abstract: Embodiments generally relate to systems and methods for extracting and visualizing user-centric communities from emails. A set of email data comprising a set of users can be identified and a communication graph comprising a center node can be generated from the email data. The center node can be removed from the communication graph and a set of communities can be determined from the remaining data. The center node can be reconnected to a center of each of the set of communities to form a community graph. The links connecting the center node with the center of each of the set of communities can have a weight calculated according to a formula. The community graph can be visualized and provided to an administrator.

Abstract: A multi-task machine learning method is performed to generate a multi-task (MT) predictor for a set of tasks including at least two tasks. The machine learning method includes: learning a multi-task decision tree (MT-DT) including learning decision rules for nodes of the MT-DT that optimize an aggregate information gain (IG) that aggregates single-task IG values for tasks of the set of tasks; and constructing the MT predictor based on the learned MT-DT. In some embodiments the aggregate IG is the largest single-task IG value of the single-task IG values. In some embodiments the machine learning method includes repeating the MT-DT learning operation for different subsets of a training set to generate a set of learned MT-DT's, and the constructing comprises constructing the MT predictor as a weighted combination of outputs of the set of MT-DT's.

Abstract: A system and method for dynamic zoning are provided. Travel demand data is received for a network which includes a set of points. The travel demand data includes values representing demand from each point to each of other point. Destination-distance values are computed which reflect the similarity between points in a respective pair, based on the travel demand data. For each pair of the points, a geo-distance value is generated which reflects the distance between locations of the points in the pair. An aggregated affinity matrix is formed by aggregating the computed geo-distance values and destination-distance values. The aggregated affinity matrix is used by a clustering algorithm to assign each of the points in the set to a respective one of a set of clusters. A representation of the clusters can be generated in which each of a set of zones encompasses the points assigned to its respective cluster.

Abstract: Aspect of the exemplary embodiment relate to a method and apparatus for automatically identifying features that are suitable for use by a classifier in assigning class labels to text sequences extracted from noisy documents. The exemplary method includes receiving a dataset of text sequences, automatically identifying a set of patterns in the text sequences, and filtering the patterns to generate a set of features. The filtering includes at least one of filtering out redundant patterns and filtering out irrelevant patterns. The method further includes outputting at least some of the features in the set of features, optionally after fusing features which are determined not to affect the classifiers accuracy if they are merged.