Morgan State University

Kevin Kornegay

Willie Lee Thompson, Ii

Md Tanvir Arafin

Denzel Hamilton

Hailu Kassa

Otily Toutsop

A safety assurance system and apparatus for improving the safety of unmanned vehicles where various computer, GPS and proximity data is collected onboard from the unmanned vehicle and transmitted to a ground/home station, where the data is assigned values according to fuzzy logic rules. The values are input to a fuzzy logic safety module and three different fuzzy logic security modules to safety and risk scores. The safety and risk scores are then applied to a decision tree to determine whether the native navigation control system should be confirmed to continue mission or overridden to hover/idle in place, land in place or return to home.

Unmanned vehicle safety assurance system

Autonomous navigation cyber-attack detection and/or avoidance techniques include visual and inertial odometry (VIO) algorithms to provide a root-of-trust during navigation, VIO algorithms that cross-validate navigation parameters using IMU and visual data, and hardware-dependent attack survival mechanisms that support autonomous systems during an attack.

Attack detection and countermeasures for autonomous navigation

An automated method and system for modeling intrusion detection on an Internet of Things network preprocess received raw data packets. The raw data packets are converted to a packet capture file, which is converted to a comma separated value (CSV) file. The CSV file is filtered to create normal and abnormal CSV files. An attack is identified in the abnormal CSV file. Features associated with the attack are labeled and classified as an attack type. The abnormal and normal CSV files are merged. Redundant data is removed from the merged file, which is added to a concatenated file with other merged files. Features are extracted from the concatenated file and a machine language (ML) model is built using the extracted features. ML classifiers are determined for each merged file for the ML model to build an ensemble ML model. A dynamic ensemble of ML classifiers detects evolving attack types.

Ensemble intrusion detection system for IOT platforms

Methods and systems are provided for managing a smart antenna system to maximize energy efficiency while maintaining spectral efficiency and signal integrity. In accordance with certain aspects of a particularly preferred embodiment, antenna beamforming may be optimized at a base station by combining a recursive least squares beamforming technique with Kaiser windowing functions to enable side lobe cancellation in the emitted beam, thus enhancing the capacity and service quality of smart antenna systems. With respect to further aspects of a particularly preferred embodiment, processing methods may be implemented at the base station of a cellular network to cluster mobile stations in a way that improves overall energy efficiency of a base station in the cellular network. More particularly, mobile stations or users may be clustered using a linear radius clustering method and a last user sector based clustering method to direct the beam emitted from the base station antenna to those sectors determined to contain the users having the greatest signal resource need.

Adaptive energy efficient cellular network

Systems and methods are disclosed for providing a trusted computing environment that provides data security in commodity computing systems. Such systems and methods deploy a flexible architecture comprised of distributed trusted platform modules (TPMs) configured to establish a root-of-trust within a heterogeneous network environment comprised of non-TPM enabled IoT devices and legacy computing devices. A data traffic module is positioned between a local area network and one or more non-TPM enabled IoT devices and legacy computing devices, and is configured to control and monitor data communication among such IoT devices and legacy computing devices, and from such IoT devices and legacy computing devices to external computers. The data traffic module supports attestation of the IoT devices and legacy computing devices, supports secure boot operations of the IoT devices and legacy computing devices, and provides tamper resistance to such IoT devices and legacy computing devices.

Growing community of inventors

Towson, MD, United States of America

Kevin Kornegay