Abstract: A machine learning system for aggregating electroencephalographic (EEG) data in preparation for downstream analysis via further machine learning models. Machine learning models can be used to assist in diagnosis of various mental health conditions, brain-computer interface, mood detection systems, or other biometric functions. Implementations of the present disclosure, employ a portion of the transformer network (the attention encoder stack) to aggregate EEG trials or EEG data segments, in a data-driven way, by ensuring the important content of each trial is not lost. Each EEG trial to be aggregated is converted into an input embedding, or a vector which numerically represents the data in the trial.

Abstract: A machine learning system for aggregating electroencephalographic (EEG) data, as well as external data, in preparation for downstream analysis via further machine learning models. Machine learning models can be used to assist in diagnosis of various mental health conditions, brain-computer interface, mood detection systems, or other biometric functions. Implementations of the present disclosure, employ a portion of the transformer network (the attention encoder stack) to aggregate EEG trials or EEG data segments, in a data-driven way, by ensuring the important content of each trial is not lost. Each EEG trial to be aggregated is converted into an input embedding, or a vector which numerically represents the data in the trial.

Abstract: In one example embodiment, a fluid induced instability detection system is provided that monitors various vibration characteristics of a turbomachine, collects vibration data in real-time, and uses the vibration data to detect and analyze changes in various operating parameters such as vibration, speed, and loading conditions, and to provide an indication of a vibration anomaly and/or potential operational risk in one or more components of the turbomachine. The vibration data can be particularly associated with certain components that are directly or indirectly impacted by a modification in process fluid flow characteristics or lubrication oil flow characteristics in the turbomachine due to various reasons such as process fluid flow disturbances, lubricating oil flow disturbances, and/or a change in turbomachine operational parameters. The fluid induced instability detection system detects abnormalities in the vibration data and provides an indication of one or more potential faults in the turbomachine.

Abstract: In one example embodiment, a fluid induced instability detection system is provided that monitors various vibration characteristics of a turbomachine, collects vibration data in real-time, and uses the vibration data to detect and analyze changes in various operating parameters such as vibration, speed, and loading conditions, and to provide an indication of a vibration anomaly and/or potential operational risk in one or more components of the turbomachine. The vibration data can be particularly associated with certain components that are directly or indirectly impacted by a modification in process fluid flow characteristics or lubrication oil flow characteristics in the turbomachine due to various reasons such as process fluid flow disturbances, lubricating oil flow disturbances, and/or a change in turbomachine operational parameters. The fluid induced instability detection system detects abnormalities in the vibration data and provides an indication of one or more potential faults in the turbomachine.

Abstract: A fluid induced instability detection system and method is provided to monitor various vibration characteristics of a turbomachine. The fluid induced instability detection system detects abnormalities in the vibration data and provides an indication of one or more potential faults in the turbomachine.

Abstract: According to one embodiment of the invention, a customizable saferoom includes a ceiling panel, a first wall panel having a first set of dimensions, a second wall panel having a second set of dimensions, a third wall panel having a third set of dimensions, and a fourth wall panel having a fourth set of dimensions. Each of the ceiling panel and the first, second, third, and fourth wall panels are coupled to at least one other of the ceiling panel, the first, second, third, and fourth wall panels to form an enclosed structure. The first, second, third, and fourth sets of dimensions are selected to optimize the volumetric capacity of the enclosed structure within the confines of a pre-existing space within a building.