Abstract: A method for ensemble machine learning includes: receiving input data and input models, the input models each having learning properties; generating perturbed data by adding noise to the input data; performing a landmarking operation on the perturbed data to generate meta-features that correlate with the learning properties of the input models; generating decision trees based on the input models and the meta-features.

Abstract: A method for managing computational resources of a data center is useable for making one or more management decisions (MD). One or more computational resources of the data center are assigned to one or more physical and/or virtual functions by MD of a decision making entity (DME). The MD are based on collected performance information of the one or more computational resources. The collected performance information is analysed considering one or more predefined performance parameters. A single performance metric (SPM) is computed representing performance and efficiency of the DME using a result of the analysis. The SPM is used by the DME for making the MD.

Abstract: A method for processing an input data matrix so as to provide co-clustering assignments of rows and columns of the input data matrix includes generating, from the input data matrix, a graph of rows in the data matrix and a graph of columns in the data matrix, determining an objective function for generating a compact representation of the input data matrix, and generating the compact representation of the input data matrix by performing alternating optimization of the objective function until a test compact representation that causes the objective function to converge is generated. The method additionally includes generating a new graph of rows and a new graph of columns from the compact representation of the input data matrix, and returning a connected component of the new graph of rows and a connected component of the new graph of columns as the co-clustering assignments of the rows and columns.

Abstract: A method for providing a typical load profile of a vehicle includes computing dwell times and maximum load stops, wherein a maximum load stop indicates a stop having a largest load on a route for a trip using route information and vehicle scheduling information based on automatic vehicle location data, computing one or more trip load profiles by identifying a load progression rate by performing a local regression procedure dividing the route into subsections such that the loads between adjacent subsections can be represented by a linear function on input of the computed maximum load, the computed dwell times, and maximum load stops, and constraining the identified load progression rate to an admissible value by evaluating the rate load progression with regard to historical dwell times and the computed maximum load stops. The method further includes computing the typical load profile based on load profiles of computed trips.

Abstract: Methods and systems for automating supervised learning tasks are provided. Feature generation in a feature space having a plurality of features using at least one predefined process for a plurality of data types is performed. A minimum set of relevant features are identified. The feature space is decreased using at least one filtering approach and the minimum set of relevant features. A Bayesian combinatorial optimization heuristic is devised to jointly identify a feature subset and a hyperparameter setting for a given query, a machine learning algorithm, and a dataset.

Abstract: A method for ensemble machine learning includes: receiving input data and input models, the input models each having learning properties; generating perturbed data by adding noise to the input data; performing a landmarking operation on the perturbed data to generate meta-features that correlate with the learning properties of the input models; generating decision trees based on the input models and the meta-features.

Abstract: A system for filtering data for a traffic control center includes: a plurality of data sources, comprising a plurality of traffic-related data sources and a weather-related data source; one or more network computing devices, configured to process data from the plurality of data sources to predict causes associated with predicted traffic incidents, and to select data from the plurality of data sources to be output to the traffic control center based on the predicted causes; and one or more output devices, located at the traffic control center, configured to display respective data selected by the one or more network computing devices.

Abstract: A method for processing an input data matrix so as to provide co-clustering assignments of rows and columns of the input data matrix includes generating, from the input data matrix, a graph of rows in the data matrix and a graph of columns in the data matrix, determining an objective function for generating a compact representation of the input data matrix, and generating the compact representation of the input data matrix by performing alternating optimization of the objective function until a test compact representation that causes the objective function to converge is generated. The method additionally includes generating a new graph of rows and a new graph of columns from the compact representation of the input data matrix, and returning a connected component of the new graph of rows and a connected component of the new graph of columns as the co-clustering assignments of the rows and columns.

Abstract: A method for managing computational resources of a data center is useable for making one or more management decisions (MD). One or more computational resources of the data center are assigned to one or more physical and/or virtual functions by MD of a decision making entity (DME). The MD are based on collected performance information of the one or more computational resources. The collected performance information is analysed considering one or more predefined performance parameters. A single performance metric (SPM) is computed representing performance and efficiency of the DME using a result of the analysis. The SPM is used by the DME for making the MD.

Abstract: A method for providing dispatching services for an on-demand transportation (ODT) service includes determining that a predictive assignment message should be transmitted to a vehicle, generating, in response to the determining that a predictive assignment should be transmitted to a vehicle, the predictive assignment message, and transmitting, to the vehicle, the predictive assignment message. Generating the predictive assignment message uses one or more prediction models computed from historical and real-time ODT service data.

Abstract: A method of filtering Floating Car Data (FCD) sources includes receiving data from the FCD sources. A plurality of indicators are computed for each of the FCD sources from the data received from the FCD sources. The indicators include at least one indicator that indicates a veracity of the data and at least one indicator that indicates a value of the data. A unified quality indicator is computed for each of the FCD sources from the respective indicators. The unified quality indicators are compared to a predetermined threshold. The data received from the FCD sources is stored excluding, based on the comparison, the data received from at least one of the FCD sources.

Abstract: A method for providing dispatching services for an on-demand transportation (ODT) service includes determining that a predictive assignment message should be transmitted to a vehicle, generating, in response to the determining that a predictive assignment should be transmitted to a vehicle, the predictive assignment message, and transmitting, to the vehicle, the predictive assignment message. Generating the predictive assignment message uses one or more prediction models computed from historical and real-time ODT service data.

Abstract: A method for incident detection in a time-evolving system (TOS), having a plurality of objects moving in time and space along predefined paths, is performed in a memory available to a computation device. The method includes, in a step a), providing predictions of at least two system parameters by using for each prediction a different prediction procedure based on observations. In a step b), the predictions are combined to a prediction ensemble. In a step c), the prediction ensemble is corrected based on an abnormal change of the system having occurred, wherein: the abnormal change is detected by monitoring distributions of deviations from the prediction ensemble, and the prediction ensemble is corrected incrementally based on a real-time learning procedure. In a step d), an incident is detected based on a result of step c).

Abstract: A method for providing a typical load profile of a vehicle includes computing dwell times and maximum load stops, wherein a maximum load stop indicates a stop having a largest load on a route for a trip using route information and vehicle scheduling information based on automatic vehicle location data, computing one or more trip load profiles by identifying a load progression rate by performing a local regression procedure dividing the route into subsections such that the loads between adjacent subsections can be represented by a linear function on input of the computed maximum load, the computed dwell times, and maximum load stops, and constraining the identified load progression rate to an admissible value by evaluating the rate load progression with regard to historical dwell times and the computed maximum load stops. The method further includes computing the typical load profile based on load profiles of computed trips.

Abstract: A system for filtering data for a traffic control center includes: a plurality of data sources, comprising a plurality of traffic-related data sources and a weather-related data source; one or more network computing devices, configured to process data from the plurality of data sources to predict causes associated with predicted traffic incidents, and to select data from the plurality of data sources to be output to the traffic control center based on the predicted causes; and one or more output devices, located at the traffic control center, configured to display respective data selected by the one or more network computing devices.