Engineering Commons^™

Real-Time Machine Learning For Quickest Detection, Yongxin Liu

Doctoral Dissertations and Master's Theses

Safety-critical Cyber-Physical Systems (CPS) require real-time machine learning for control and decision making. One promising solution is to use deep learning to discover useful patterns for event detection from heterogeneous data. However, deep learning algorithms encounter challenges in CPS with assurability requirements: 1) Decision explainability, 2) Real-time and quickest event detection, and 3) Time-eficient incremental learning.

To address these obstacles, I developed a real-time Machine Learning Framework for Quickest Detection (MLQD). To be specific, I first propose the zero-bias neural network, which removes decision bias and preferabilities from regular neural networks and provides an interpretable decision process. Second, I discover …

Uas Detection And Negation, Houbing Song, Yongxin Liu, Jian Wang

Publications

Unauthorized operation of a UAV may present privacy or security risks. A software-defined radio (SDR) or other receiver can be used to monitor a specified range of frequencies to provide detection of wireless communication signals suspected of relating to UAV operation. A protocol detector corresponding to a trained classifier can be applied to data packets demodulated by the SDR. A transmitter can then be triggered to provide warnings by injecting warning data into a video channel in response to the detected protocol. Control of the UAV can be established by transmitting simulated control commands that overwhelm the signals received from …

Drones Detection Using Smart Sensors, Aishah Moafa

Doctoral Dissertations and Master's Theses

Drones are modern and sophisticated technology that have been used in numerous fields. Nowadays, many countries use them in exploration, reconnaissance operations, and espionage in military operations. Drones also have many uses that are not limited to only daily life. For example, drones are used for home delivery, safety monitoring, and others. However, the use of drones is a double-edged sword. Drones can be used for positive purposes to improve the quality of human lives, but they can also be used for criminal purposes and other detrimental purposes. In fact, many countries have been attacked by terrorists using smart drones. …

Security Of The Internet Of Things: Vulnerabilities, Attacks And Countermeasures, Ismail Butun, Houbing Song, Patrik Osterberg

Publications

Wireless Sensor Networks (WSNs) constitute one of the most promising third-millennium technologies and have wide range of applications in our surrounding environment. The reason behind the vast adoption of WSNs in various applications is that they have tremendously appealing features, e.g., low production cost, low installation cost, unattended network operation, autonomous and longtime operation. WSNs have started to merge with the Internet of Things (IoT) through the introduction of Internet access capability in sensor nodes and sensing ability in Internet-connected devices. Thereby, the IoT is providing access to huge amount of data, collected by the WSNs, over the Internet. Hence, …

Determination Of The Parameter Limits For Artificial Non-Random Microwave Signal Detection, Irvin Lee Burough

Master's Theses - Daytona Beach

The Doppler shift of small bandwidth (several Hertz) microwave signals makes identification of spectral features difficult; the Doppler individual bandwidth shift can be a factor of hundreds or thousands of times greater than the bandwidth. A computer model supplied by the National Aeronautics and Space Administration's (NASA) Search for Extra-Terrestrial Intelligence (SETI) project, which can simulate radio frequency interference (RFI) and a buried ETI signal, will determine the limits of the signal-to-noise ratio (SNR) and false alarm threshold for identification of the signal after Doppler shifting. By running the model on a MicroVAX II computer, it will be possible to …