Abstract: Systems and methods for machine learning of medical records are provided. The system can execute multiple machine learning models on the medical records in parallel using multi-threaded approach wherein each machine learning model executes using its own, dedicated computational thread in order to significantly speed up the time with which relevant information can be identified from documents by the system. The multi-threaded machine learning models can include, but are not limited to, sentence classification models, comorbidity models, ICD models, body parts models, prescription models, and provider name models. The system can also utilize combined convolutional neural networks and long short-term models (CNN+LSTMs) as well as ensemble machine learning models to categorize sentences in medical records. The system can also extract service provider, medical specializations, and dates of service information from medical records.

Abstract: Methods and systems for assigning a wireless communication device (WCD) to a wireless coverage are a based on early termination gain (ETG) are presented. In particular, a RAN may receive a request, from a WCD, for an assignment to one of a plurality of wireless coverage areas. In response to receiving the request, the RAN may select a wireless coverage area of the plurality that has a highest ETG, and assign the WCD to the selected wireless coverage area. Prior to selecting this wireless coverage area, the RAN may optionally remove one or more wireless coverage areas with high utilization from consideration.

Abstract: Methods and systems for assigning a wireless communication device (WCD) to a wireless coverage are a based on early termination gain (ETG) are presented. In particular, a RAN may receive a request, from a WCD, for an assignment to one of a plurality of wireless coverage areas. In response to receiving the request, the RAN may select a wireless coverage area of the plurality that has a highest ETG, and assign the WCD to the selected wireless coverage area. Prior to selecting this wireless coverage area, the RAN may optionally remove one or more wireless coverage areas with high utilization from consideration.

Abstract: An embodiment of the invention is directed toward identifying a number of high-ranking sectors requiring additional communication resources in a network composed of a number of sectors. A set of wireless-service subscribers that have churned are identified. Various sector profile data is captured for sectors serving the churners. The sectors are ranked based on the sector profile data that is collected. A number of high-ranking sectors are identified, based on the ranking.

Abstract: A location of a mobile station is estimated based on wireless communications between the mobile station and a wireless telecommunications network. Call measurement data is obtained for a call involving the mobile station and a plurality of base station antennas. The call measurement data includes round-trip delay (RTD) measurements and received signal strength (RSS) measurements. The most significant one or more base station antennas involved in the call are identified. An expected signal strength is calculated for each significant base station antenna, according to a wireless propagation model that accounts for terrain around the base station antennas. For each significant base station antenna, the corresponding expected signal strength, RTD measurement, and RSS measurement are used to calculate an adjusted RTD value. The one or more adjusted RTD values calculated for the one or more significant base station antennas are used to estimate the mobile station's location.

Abstract: A location of a mobile station is estimated based on wireless communications between the mobile station and a wireless telecommunications network. Call measurement data is obtained for a call involving the mobile station and a plurality of base station antennas. The call measurement data includes round-trip delay (RTD) measurements and received signal strength (RSS) measurements. The most significant one or more base station antennas involved in the call are identified. An expected signal strength is calculated for each significant base station antenna, according to a wireless propagation model that accounts for terrain around the base station antennas. For each significant base station antenna, the corresponding expected signal strength, RTD measurement, and RSS measurement are used to calculate an adjusted RTD value. The one or more adjusted RTD values calculated for the one or more significant base station antennas are used to estimate the mobile station's location.

Abstract: The present invention provides a method and system for defining the mean opinion score (MOS) as a function of frame error rate (FER) and pilot signal strength. In an embodiment of the invention, an entity receives MOS scores that have been obtained using subjective tests for certain calls made within the network. Next, the entity receives FER and pilot signal strength samples that have been obtained for the calls for which MOS scores have been subjectively obtained. Finally, the entity calculates an equation for the MOS as a function of FER and pilot signal strength using a non-linear regression analysis.

Abstract: A wireless communication system for monitoring a communication service comprises a first set of communication devices located in a first set of geographic areas configured to receive the communication service and determine first performance data. A communication network is configured to determine first network data for the communication service. A service monitoring system is configured to process the first performance data and the first network data to generate a communication service model. A second set of communication devices located in a second set of geographic areas is configured to receive the communication service and determine second performance data. The communication network is configured to determine second network data. The service monitoring system is configured to process the second network data with the communication service model to generate model performance data, and compare the model performance data to the second performance data to validate the communication service model.

Abstract: What is disclosed is a method of operating a processing system to relocate wireless communication equipment. The method includes receiving customer data and performance data for wireless communication equipment located at a plurality of potential donor sites, and receiving geographic information for a target relocation site. The method also includes processing the customer data, the performance data, and the geographic information to determine a relocation score for each of the wireless communication equipment located at the plurality of potential donor sites, and selecting wireless communication equipment of at least one of the plurality of potential donor sites for relocation to the target relocation site based upon the relocation score.