Abstract: A method and apparatus for classifying an image. In one example, the method may include receiving one or more images associated with a source domain and one or more images associated with a target domain, identifying one or more source domain features based on the one or more images associated with the source domain, identifying one or more target domain features based on the one or more images associated with the target domain, training a conditional maximum mean discrepancy (CMMD) engine based on a difference between the one or more source domain features and the one or more target domain features, applying the CMMD engine to the one or more images associated with the target domain to generate one or more labels for each unlabeled target image of the one or more images associated with the target domain and classifying each one of the one or more images in the target domain using the one or more labels.

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 method and system are disclosed for generating a list of trips on an associated transportation network, the list ranked in accordance with time-dependent modeling of passenger preferences. User preferences of choosing a specific public transportation service or change point are modeled by a set of latent variables. Any actual trip on the network is converted into a set of pairwise preferences implicitly made by the passenger during the trip. Sequences of services matrices and change points matrices from the retrieved set of trips and non-negative factorization of the services and change points matrices is performed to smooth the matrices. The set of pairwise preferences are used to learn a ranking function and the output of a journey planner is re-ranked using the ranking function.

Abstract: A machine learning method operates on training instances from a plurality of domains including one or more source domains and a target domain. Each training instance is represented by values for a set of features. Domain adaptation is performed using stacked marginalized denoising autoencoding (mSDA) operating on the training instances to generate a stack of domain adaptation transform layers. Each iteration of the domain adaptation includes corrupting the training instances in accord with feature corruption probabilities that are non-uniform over at least one of the set of features and the domains. A classifier is learned on the training instances transformed using the stack of domain adaptation transform layers. Thereafter, a label prediction is generated for an input instance from the target domain represented by values for the set of features by applying the classifier to the input instance transformed using the stack of domain adaptation transform domains.

Abstract: A method for domain adaptation of samples includes receiving training samples from a plurality of domains, the plurality of domains including at least one source domain and a target domain, each training sample including values for a set of features. A domain predictor is learned on at least some of the training samples from the plurality of domains and respective domain labels. Domain adaptation is performed on the training samples using marginalized denoising autoencoding. This generates a domain adaptation transform layer (or layers) that transforms the training samples to a common adapted feature space. The domain adaptation employs the domain predictor to bias the domain adaptation towards one of the plurality of domains. Domain adapted training samples and their class labels can be used to train a classifier for prediction of class labels for unlabeled target samples that have been domain adapted with the domain adaptation transform layer(s).

Abstract: A method for estimating travel demand in a transportation network includes receiving a dataset of trips. The trips were taken in the transportation network and are each represented by an origin-destination pair and a departure time. A trip can include a sequence of legs. Each trip is described by a vector of modalities. For trips that include the sequence of legs, boarding and alighting stops are estimated. An empirical trip distribution is generated for each modality for given origin-destination stops. The empirical trip distribution is fitted to a specific family of probability distributions. At least one of the generating the empirical trip distribution for a given modality and the fitting the empirical trip distribution to the probability distributions is performed with a processor.

Abstract: A machine learning method operates on training instances from a plurality of domains including one or more source domains and a target domain. Each training instance is represented by values for a set of features. Domain adaptation is performed using stacked marginalized denoising autoencoding (mSDA) operating on the training instances to generate a stack of domain adaptation transform layers. Each iteration of the domain adaptation includes corrupting the training instances in accord with feature corruption probabilities that are non-uniform over at least one of the set of features and the domains. A classifier is learned on the training instances transformed using the stack of domain adaptation transform layers. Thereafter, a label prediction is generated for an input instance from the target domain represented by values for the set of features by applying the classifier to the input instance transformed using the stack of domain adaptation transform domains.

Abstract: Training instances from a target domain are represented by feature vectors storing values for a set of features, and are labeled by labels from a set of labels. Both a noise marginalizing transform and a weighting of one or more source domain classifiers are simultaneously learned by minimizing the expectation of a loss function that is dependent on the feature vectors corrupted with noise represented by a noise probability density function, the labels, and the one or more source domain classifiers operating on the feature vectors corrupted with the noise. An input instance from the target domain is labeled with a label from the set of labels by operations including applying the learned noise marginalizing transform to an input feature vector representing the input instance and applying the one or more source domain classifiers weighted by the learned weighting to the input feature vector representing the input instance.

Abstract: Methods and systems for estimating airport usage demand. Airport parking traffic usage data and flight-time table data can be compiled with respect to an airport (or more than one airport). The airport parking traffic usage data and flight-time table data can be analyzed using an efficient time matching approach (e.g., a time segment matching algorithm). An efficient method to match passengers and flights is introduced. Passenger behavior can be estimated with respect to the airport based on the airport parking traffic usage data and flight-time table data.

Abstract: A method and system are disclosed for generating a list of trips on an associated transportation network, the list ranked in accordance with time-dependent modeling of passenger preferences. User preferences of choosing a specific public transportation service or change point are modeled by a set of latent variables. Any actual trip on the network is converted into a set of pairwise preferences implicitly made by the passenger during the trip. Sequences of services matrices and change points matrices from the retrieved set of trips and non-negative factorization of the services and change points matrices is performed to smooth the matrices. The set of pairwise preferences are used to learn a ranking function and the output of a journey planner is re-ranked using the ranking function.

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 classification method includes receiving a collection of samples, each sample comprising a multidimensional feature representation. A class label prediction for each sample in the collection is generated with one or more pretrained classifiers. For at least one iteration, each multidimensional feature representation is augmented with a respective class label prediction to form an augmented representation, a set of corrupted samples is generated from the augmented representations, and a transformation that minimizes a reconstruction error for the set of corrupted samples is learned. An adapted class label prediction for at least one of the samples in the collection is generated using the learned transformation and information is output, based on the adapted class label prediction. The method is useful in predicting labels for target samples where there is no access to source domain samples that are used to train the classifier and no access to target domain training data.

Abstract: A domain-adapted classification system and method are disclosed. The method includes mapping an input set of representations to generate an output set of representations, using a learned transformation. The input set of representations includes a set of target samples from a target domain. The input set also includes, for each of a plurality of source domains, a class representation for each of a plurality of classes. The class representations are representative of a respective set of source samples from the respective source domain labeled with a respective class. The output set of representations includes an adapted representation of each of the target samples and an adapted class representation for each of the classes for each of the source domains. A class label is predicted for at least one of the target samples based on the output set of representations and information based on the predicted class label is output.

Abstract: Methods, systems, and processor-readable media for the stochastic optimization of public transport schedules. A real-world collection of transit instances can be derived from a transport system and fed as input to a two-stage stochastic program. A schedule offset can be relaxed in the two-stage stochastic program to allow the two-stage stochastic program to operate according to the real-world collection of transit instances. An optimized transport schedule can then be derived from the two-stage stochastic program for use by the transport system based on the schedule offset and the real-world collection of transit instances.

Abstract: A tag recommendation for an item to be tagged is generated by: selecting a set of candidate neighboring items in an electronic social network based on context of items in the electronic social network respective to an owner of the item to be tagged; selecting a set of nearest neighboring items from the set of candidate neighboring items based on distances of the candidate neighboring items from the item to be tagged as measured by an item comparison metric; and selecting at least one tag recommendation based on tags of the items of the set of nearest neighboring items. The item comparison metric may comprise a Mahalanobis distance metric trained on the set of candidate neighboring items to correlate the trained Mahalanobis distance between pairs of items of the set of candidate neighboring items with an overlap metric indicative of overlap of the tag sets of the two items.

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: 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: Methods and systems for estimating airport usage demand. Airport parking traffic usage data and flight-time table data can be compiled with respect to an airport (or more than one airport). The airport parking traffic usage data and flight-time table data can be analyzed using an efficient time matching approach (e.g., a time segment matching algorithm). An efficient method to match passengers and flights is introduced. Passenger behavior can be estimated with respect to the airport based on the airport parking traffic usage data and flight-time table data.

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.