Effective And Scalable Integrative Geocoder for Massive Address Dataset (EaserGeocoder)

An integrative geocoding model, which utilizes multiple open data sources as underlying references. Background: With an increased accessibility of large scale open data, public health studies are able to take advantage of integrative spatial big data to increase the spatial resolution to community or neighborhood level. Technology Overview: The terminology geocoding, utilizes multiple open data sources as underlying references. Implemented is a open source geocoding system. Taken into consideration is the information type which is private address of patients which is highly sensitive. Easer geocoder is a novel open source geocoder for effectively geocoding massive address data sets. Machine learning approach allows for multiple sources, via contributions of government and communities, to select the best answer from result candidates. The system provides high scalability, the implementation is done through parallel processing. By using multiple free data sources, current apprach is comparable to competing high tech vendors. Finally, it is deployed using HIPPA complaint enviornment Advantages: Developed is a high accuracy, novel algorithm. The novel machine learning method for solving the problem of choosing the best answer is done by new approach in ground truth data set and high scalability. Applications: Intellectual Property Summary: US Provisional Filed Stage of Development: Working prototype available for demonstartion. Licensing Potential: Licensing Status: Exclusive License - All Fields Additional Information: Department of Biomedical Inforamtics, Department of Computer Science Geographic Information Systems, Geocoding, Spatio-Textual Searching, Knowledge Discovery https://stonybrook.technologypublisher.com/files/sites/computer-software1.jpg , https://stonybrook.technologypublisher.com/files/sites/it-21.jpg
Patent Information:
Technology/Start-up ID: