The present disclosure relates to a method for filtering selectively obstacle to be an obstacle to machine learning according to a learning purpose and a system thereof. A system for filtering obstacle data in machine learning of medical images may include an obstacle data definition unit configured to receive definitions of obstacle data according to a machine learning purpose; a filter generation unit configured to generate a filter for filtering the obstacle data; and a filtering unit configured to remove obstacle data in machine learning using the generated filter.

A method for use with a computing device is provided. The method may include inputting an input data set into a first private artificial intelligence model generated using a first private data set and a second private artificial intelligence model generated using a second private data set. The method may further include receiving a first result data set from the first private artificial intelligence model and receiving a second result data set from the second private artificial intelligence model. The method may further include training an adaptive co-distillation model with the input data set and the first result data set. The method may further include training the adaptive co-distillation model with the input data set and the second result data set. The adaptive co-distillation model may not be trained on the first private data set or the second private data set.

A device may receive a hash table that includes lists of protocol detectors, wherein the hash table is generated based on historical process data identifying potential process variables associated with an industrial control system. The device may receive a packet identifying potential process variables associated with the industrial control system, and may extract, from the packet, packet data identifying a source address, a destination address, a port, and a transport protocol. The device may compare the packet data with data in the hash table to identify a set of lists of protocol detectors, and may process the packet data, with the set of lists of protocol detectors, to determine a matching protocol, no matching protocol, or a potential matching protocol for the packet. The device may perform one or more actions based on determining the matching protocol, no matching protocol, or the potential matching protocol for the packet.

A method for controlling a robotic device is presented. The method includes positioning the robotic device within a task environment. The method also includes mapping descriptors of a task image of a scene in the task environment to a teaching image of a teaching environment. The method further includes defining a relative transform between the task image and the teaching image based on the mapping. Furthermore, the method includes updating parameters of a set of parameterized behaviors based on the relative transform to perform a task corresponding to the teaching image.

A model learning device provided with: an error-added movement locus generation unit for adding an error to movement locus data for action learning that represents the movement locus of a subject and to which is assigned an action label that is information representing the action of the subject, and thereby generating error-added movement locus data; and an action recognition model learning unit for learning a model, using at least the error-added movement locus data and learning data created on the basis of the action label, by which model the action of some subject can be recognized from the movement locus of the subject. Thus, it is possible to provide a model by which the action of a subject can be recognized with high accuracy on the basis of the movement locus of the subject estimated using a camera image.

Methods and systems are provided for detecting a mental health condition. Structured and unstructured information is analyzed using natural language processing to extract information including clinical data values and medical concepts pertaining to a user. Reference medical information is evaluated using natural language processing to correlate medical data with mental health conditions. A classification for a mental health condition of the user is determined using a machine learning model and based on the extracted information and correlations, wherein the extracted information includes blood analysis for the user. The user is assigned to a segment of users based on the extracted information. A treatment for the mental health condition of the user is indicated based on the classification and the assigned segment of users.

Embodiments detect fraud of risk targets that include both customer accounts and cashiers. Embodiments receive historical point of sale (“POS”) data and divide the POS data into store groupings. Embodiments create a first aggregation of the POS data corresponding to the customer accounts and a second aggregation of the POS data corresponding to the cashiers. Embodiments calculate first features corresponding to the customer accounts and second features corresponding to the cashiers. Embodiments filter the risk targets based on rules and separate the filtered risk targets into a plurality of data ranges. For each combination of store groupings and data ranges, embodiments train an unsupervised machine learning model. Embodiments then apply the unsupervised machine learning models after the training to generate first anomaly scores for each of the customer accounts and cashiers.

Embodiments detect fraud of risk targets that include both customer accounts and cashiers. Embodiments receive historical point of sale (“POS”) data and divide the POS data into store groupings. Embodiments create a first aggregation of the POS data corresponding to the customer accounts and a second aggregation of the POS data corresponding to the cashiers. Embodiments calculate first features corresponding to the customer accounts and second features corresponding to the cashiers. Embodiments filter the risk targets based on rules and separate the filtered risk targets into a plurality of data ranges. For each combination of store groupings and data ranges, embodiments train an unsupervised machine learning model. Embodiments then apply the unsupervised machine learning models after the training to generate first anomaly scores for each of the customer accounts and cashiers.

A framework for dynamic network resource allocation and energy saving based on the real-time environment, radio network information, and machine learning (ML) can be utilized via a radio access network (RAN) intelligent controller (RIC). Real-time and predicted network utilization can facilitate resource and energy savings by leveraging the RIC platform. For example, a network information base (NIB) in the RIC platform can collects RAN and user equipment (UE) resource related information in real time and provides the abstraction of the access network in the real time. ML can predict real-time information about the UEs at time t based on data analytics and real time radio resource needs. The RIC can then instruct the network to reduce or increase resources.

In order to facilitate electronic meeting scheduling and coordination, systems and methods are disclosed including receiving, by a processor, a plurality of electronic meeting requests to schedule a meeting. The processor determines, for each electronic meeting request, meeting room needs. A meeting scheduling machine learning model is utilized to predict parameters of meeting room objects representing the candidate meeting rooms based at least in part on the meeting room needs, schedule information associated with a respective electronic meeting request and location information associated with the respective electronic meeting request. The processor causes an indication of the candidate meeting rooms to display in response to the electronic meeting request on a screen of computing devices associated with the respective attendees based at least in part on the predicted parameters. The processor receives a selection of the respective candidate meeting rooms from the respective attendees, and dynamically secures each candidate meeting room.