The goal is to research and develop a Quality of Information (QOI) Maximizing Information Acquisition Framework (QMAF) for event prediction that goes beyond the limitations of traditional approaches of heuristic/closed form optimization formulations (and its inherent computational complexities) for selection of sensor/data selection. The concept for deriving the QOI optimizing sensor orchestration strategy is looked at as two sub problems a) for a set of random sensor selections, build separate event prediction models and compute the performance accuracies, and b) have a second predictive model learn the relationship between sensor selections and prediction accuracy. The first step calibrates multiple event prediction models for a diverse set of sensor selections, and also generates accuracy data that is used by the second model. The second model can answer the question of the expected accuracy for a given sensor selection, and can point to sensor selection strategies that maximizes the accuracy at minimal acquisition costs. The effort leverages deep learning architectures for complex feature preprocessing, intelligent sampling strategies, as well as active learning algorithms that help supply informative samples for the accuracy prediction problem.
SBIR Phase I
QOI Maximizing Information Acquisition Framework
Agency: Department of Defense
Branch: Air Force
Department of Transportation Selects KBSI to Develop Mobile Application to Help Inventory and Assess Sidewalks
March 7, 2016 – KBSI has been selected by Volpe, The National Transportation Systems Center of the U.S. Department of Transportation to develop a mobile application for the collection and assessment of the U.S. sidewalk inventory.
Under the terms of the Phase II Small Business Innovation Research (SBIR) contract, KBSI will utilize recent advances in social networks, crowd sourcing, mobile data collection methods, and data mining techniques to provide integrated sidewalk datasets for analysis. The software solution, a mobile application called MySidewalk™, will facilitate the collection of sidewalk inventories and support directed insight decision making.
Built with open architectures and component technologies, MySidewalk™ will be developed with significant inputs from our partners, City of College Station, TX and Texas Transportation Institute making the solution amenable to a wide variety of public works crowd source collection efforts as well as other public entities such as healthcare, entertainment, education management work areas.
January 21, 2015 – KBSI received notification that its proposal for the MySidewalk™ application has been selected for award by the Department of Transportation Small Business Innovative Research program. “MySidewalk™” is a mobile application that will facilitate the crowd-sourced collection of sidewalk inventory and condition assessment data. The tool will utilize the recent advances in social networks, mobile data collection, and data mining to provide integrated sidewalk data-sets. The tool will be developed with significant inputs from our partners, City of College Station, TX and Texas Transportation Institute.
The TraceLogic initiative is developing methods, processes, and algorithms to decipher the hidden rules or logic of complex flight operations aboard Navy aircraft carriers. The TraceLogic technology will help the Navy to better understand and address the technical and pragmatic problems associated with improving flight operation performance.
The Text Analytics Situation Awareness Toolkit (T-SAT) will allow users to quickly build text analytics-based systems that support the research and analysis of disparate, unstructured text sources. T-SAT uses an advanced object model that allows users to combine text analytics algorithms and create complex research and analysis scenarios.
The ADVICE initiative is developing an experimental framework that improves the situational awareness of cyber systems under attack. The initiative will provide innovative human-computer interaction and visualization technology for developing cyber security controls, improving cyber situational awareness, and evaluating cyber security control architectures.
The CDAT initiative is designing and developing a toolkit that will help clinicians, healthcare administrators, and public health professionals to compare the effectiveness of different clinical practices, including preventive and treatment modalities.
The Cohort Development and Analysis Toolkit (CDAT) will allow healthcare professionals to better leverage the large amounts of healthcare data available in electronic health records, facilitating cohort development and analysis along the entire healthcare spectrum: healthcare providers, patients, systems and processes, and case management/discharge planning. By providing intuitive interfaces and workflows that are designed to support a medical practitioner rather than an IT or data expert, CDAT will make data mining and analytics more accessible to the medical community without the need for statisticians or data mining professionals.Continue reading
The Collaborative Analysis and Knowledge Exploration (CAKE) initiative, now in Phase II, is designing a semantic framework that supports information discovery, sense making, and presentation in dynamic, collaborative environments. In Phase II, KBSI is validating the capability to create semantic knowledge from multi-modal text and image data feeds using semantic tagging and collaborative visual approaches.