Abstract: An automated training method enhances conversational effectiveness of a system participant interacting with a virtual client. The method operates on received speech input to produce text. A speech effectiveness analysis processor receives both the speech and text and produces quantified metrics measuring speech effectiveness based on the input parameters. Personalized feedback is generated based on the quantified metrics and is transmitted to the system participant. A virtual client dialog is generated using a dynamic simulation processor. The virtual client dialog is based on the quantified metrics, such that the virtual client responds to the speech input using the generated dialog.

Abstract: The disclosed embodiments illustrate methods and systems for managing allocation of transportation services. The method includes receiving real-time vehicle data of vehicles of a plurality of service types from sensors associated with the vehicles. The method further includes detecting an availability status of each of the vehicles based on at least the received real-time vehicle data and a service request for a vehicle of a preferred service type for travel by a customer, to determine available service types. The method further includes rendering, in response to the service request, at least the available service types that comprises at least a flexible service type, at a user interface of a customer-computing device. The method further includes allocating the transportation services of the service provider to the customer based on a selection of a service type from the rendered plurality of available service types by the customer.

Abstract: A historical task database relating vehicle rollout decisions, vehicle maintenance states and subsequent deteriorations is created. A pattern analyzer may use an item-set mining algorithm on the task database to recommend whether a vehicle with its current maintenance state should be deployed. A supervisor uses this recommendation to make a rollout decision. These decisions are added to the database. Heuristic rules are defined to determine if the rollout decision was correct. The system to learns when a supervisor continues to make costly rollout errors. The system also discovers combinations of defects that lead to a rapid deterioration and makes recommendations that the vehicle be sent for maintenance rather than being rolled out.

Abstract: A neural network is used to model to model the joint distribution of attributes across multiple health surveys. These multiple health surveys include large scale survey datasets and small scale survey datasets. The neural network model is trained using a combined dataset of the large scale survey datasets and the small scale survey datasets. The large scale survey datasets and the small scale survey datasets may include missing value indicators. The joint distribution of attributes modeled by the neural network model are the used to impute substitute values for the missing values to thereby create an output large scale dataset that does not include missing values.

Abstract: A method and system is presented for dynamically predicting hotspots (predictive of a high volume of event occurrences) in a geographic location. The method calculates a hotspot probability measure for each grid within this geographic location by summing probability of predicted volume bucket with probabilities of all higher buckets (buckets are ordinal here). The method also calculates a hotspot score for each grid based on the corresponding hotspot probability measure, selects a pre-defined number of grids having the highest hotspot scores as predicted hotspots, and generates an alert indicating the predicted hotspots and displaying the alert on a predictive GUI, showing the multiple grids.

Abstract: A system and method for managing a multiplicity of motor vehicle parking spaces through a server is provided. Smart parking devices and vehicle occupancy sensors that are each physically proximate to and which correspond to at least one of the parking spaces is interfaced with the server. Parking availability indicators that are each associated with at least one of the parking spaces is interfaced with the server. Street sweeping activity affecting the parking spaces is planned and comprising times and dates over which street sweeping of the parking spaces will occur. Any requests for reserving the use of the parking spaces during the street sweeping activity is denied. The parking availability indicators are activated associated with the parking spaces affected by the street sweeping activity. Occupancy of each of the parking spaces by a motor vehicle is sensed through the nearest vehicle occupancy sensor.

Abstract: A method, non-transitory computer readable medium and apparatus for calculating a by spot occupancy of a parking lot are disclosed. For example, the method includes receiving an indication of a triggering event, sending a query to receive a first image and a second image in response to the triggering event, receiving the first image and the second image, analyzing the first image and the second image to determine a change in an occupancy status of a parking spot within the parking lot and calculating the by spot occupancy of the parking lot based on the change in the occupancy status of the parking spot.

Abstract: Systems and methods providing user privacy in association with decentralized ledger technology are disclosed. Improved methods and systems for access control are disclosed wherein an access request can be received at the distributed ledger to fetch a data file without disclosing requester identity, that can verify the access request at the decentralized ledger as a legitimate request or as a malicious/faulty request, and can assist a user of a legitimate request to access the data and deny access to malicious/faulty requests that are compatible with a decentralized ledger environment.

Abstract: A neural network is used to model to model the joint distribution of attributes across multiple health surveys. These multiple health surveys include large scale survey datasets and small scale survey datasets. The neural network model is trained using a combined dataset of the large scale survey datasets and the small scale survey datasets. The large scale survey datasets and the small scale survey datasets may include missing value indicators. The joint distribution of attributes modeled by the neural network model are the used to impute substitute values for the missing values to thereby create an output large scale dataset that does not include missing values.

Abstract: A method and method for natural language generation employ a natural language generation model which has been trained to assign an utterance label to a new text sequence, based on features extracted from the text sequence, such as parts-of-speech. The model assigns an utterance label to the new text sequence, based on the extracted features. The utterance label is used to guide the generation of a natural language utterance, such as a question, from the new text sequence. The system and method find application in dialog systems for generating utterances, to be sent to a user, from brief descriptions of problems or solutions in a knowledge base.

Abstract: A method for detecting a double-parked vehicle includes identifying a parking region in video data received from an image capture device monitoring the parking region. The method includes defining an enforcement region at least partially surrounding the parking region. The method includes detecting a stationary vehicle in the enforcement region. The method includes determining the occurrence of an event relative to the stationary vehicle. In response to the determined occurrence of the event, the method includes classifying the stationary vehicle as being one of double parked and not double parked.

Abstract: Systems, methods, and processing nodes determine and perform preventive maintenance on a transport vehicle in a transportation system. The method includes extracting features for previous incidents that have occurred to a plurality of transport vehicles in the transportation system. The method also includes determining a criticality of types of incidents based on the features extracted. The method includes predicting, based on the criticality of types of incidents and the features extracted, details of at least one future incident for a first transport vehicle from the plurality of transport vehicles. The details include a predicted type of the at least one future incident, a predicted time of the at least one future incident, and a predicted criticality of the at least one future incident. Additionally, the method includes performing a prescriptive action for the first transport vehicle to mitigate the at least one future incident in the first transport vehicle.

Abstract: A system for acquiring multi-angle images of a product includes a workstation having a working surface for placing a product, a camera supporting member having a vertical axis, and an image capturing device movably attached to the camera supporting member so that it may move along the vertical axis of the camera supporting member. The system captures and analyzes a digital image of a product to detect the vertical center of the product, and adjusts the position of the image capturing device along the vertical axis so that the vertical center of the product is proximate to the vertical center of the image. The system may also have a turntable and additionally rotate the turntable at multiple capturing angles and capture one or more additional digital images of the product at various capturing angles and store the one or more additional images in a product database.

Abstract: A method, non-transitory computer readable medium and apparatus for performing a person re-identification using an overhead view image are disclosed. For example, the method includes receiving a plurality of overhead view images, detecting a target person in one or more of the plurality of overhead view images, creating a probe image of the target person, receiving a selection of the probe image containing the target person, selecting one or more of the plurality of processed images that has a similar distortion profile as a distortion profile of the probe image based on a radial distance of the target person from a center of a respective overhead view image of the plurality overhead view images used to generate the probe image and performing the person-re-identification of the target person using the one or more of the plurality of processed images that are selected.

Abstract: A system for acquiring multi-angle images of a product includes a workstation having a working surface for placing a product, a camera supporting member having a vertical axis, and an image capturing device movably attached to the camera supporting member so that it may move along the vertical axis of the camera supporting member. The system captures and analyzes a digital image of a product to detect the vertical center of the product, and adjusts the position of the image capturing device along the vertical axis so that the vertical center of the product is proximate to the vertical center of the image. The system may also have a turntable and additionally rotate the turntable at multiple capturing angles and capture one or more additional digital images of the product at various capturing angles and store the one or more additional images in a product database.

Abstract: A system for acquiring multi-angle images of a product includes a workstation having a working surface for placing a product, a camera supporting member having a vertical axis, and an image capturing device movably attached to the camera supporting member so that it may move along the vertical axis of the camera supporting member. The system captures and analyzes a digital image of a product to detect the vertical center of the product, and adjusts the position of the image capturing device along the vertical axis so that the vertical center of the product is proximate to the vertical center of the image. The system may also have a turntable and additionally rotate the turntable at multiple capturing angles and capture one or more additional digital images of the product at various capturing angles and store the one or more additional images in a product database.

Abstract: A video surveillance method and system involves transitioning pixel intensities in a region associated with a fixed location from background values to values representing an image of an object when the object is abandoned at a fixed location in a scene in a video, and identifying an instance of time in the video when the object is abandoned, based on the transitioned pixel intensities resulting from the transitioning of the pixel intensities.

Abstract: A system and method for motivating parking enforcement officer performance with the aid of a digital computer is provided. A time-based active representational model of the city is created by fusing sensory data collected from various sources around a city with numerical data gleaned from historical and on-going activities, including parking regulation citation and warning numbers, resource allocations, and so on. The model can be used to form quantitative predictions of expected violations, revenue stream, and so forth, that can then be used as recommendations as to where to enforce and when, so as to maximize the utilization of the limited resources represented by the officers on the street. Moreover, the performance of the officers can be weighed against expectations of performance postulated from the quantitative predictions.

Abstract: A system and method for managing coverage of parking enforcement for a neighborhood with the aid of a digital computer is provided. A time-based active representational model of the city is created by fusing sensory data collected from various sources around a city with numerical data gleaned from historical and on-going activities, including parking regulation citation and warning numbers, resource allocations, and so on. The model can be used to form quantitative predictions of expected violations, revenue stream, and so forth, that can then be used as recommendations as to where to enforce and when, so as to maximize the utilization of the limited resources represented by the officers on the street. Moreover, the performance of the officers can be weighed against expectations of performance postulated from the quantitative predictions.

Abstract: Datasets relating time information to crime occurrences in the geographical regions are received. Time based crime patterns are extracted. Based on similarities among the crime patterns, the geographical regions are clustered. A selected time series dataset is augmented with a second time series dataset from the same cluster. Based on the augmented time series dataset, a new crime pattern is extracted. Based on the new crime pattern, a crime forecast is made for the selected geographical region.