Perceptronics Solutions (United States)

Wideband spectrum sensing and awareness is important to ensure wireless security. Specifically, accurate detection and labeling of active transmissions is necessary for further analysis and classification. In this work, we propose WHIRLS, a digital signal processing method for detecting and labeling RF signals in a wideband spectrum. WHIRLS is able to generate accurate labels with independent time and frequency resolutions, making it flexible in various RF environments. We demonstrate the effectiveness and consistency of WHIRLS in both synthetic and over-the-air dataset and make the code public for future research.

Ethical decision-making in artificial intelligence (AI) is inherently complex, context-dependent, and influenced by competing priorities. This paper presents a Bayesian ethical alignment modeling approach designed to capture, model, and calibrate human ethical values for AI decision-making. Unlike rule-based approaches, our method encodes organizational ethics within a probabilistic framework, allowing for dynamic updates and structured reasoning. We outline a structured methodology for elicitation, calibration, and validation, tested in high-stakes scenarios. We posit that this framework would enable AI to align with human ethical priorities while maintaining adaptability, scalability, and transparency.

Unmanned aerial vehicles (UAVs) are useful for commercial, recreational, and military applications, but they can also be used by malicious attackers and pose security threats. Therefore, it is important to monitor their occurrences and ensure their compliance. Radio frequency signals can be leveraged for such task. However, commercial UAVs often adopt the frequency hopping spread spectrum signals and proprietary protocols, which makes them more challenging to detect. While prior works have studied the UAV detection and classification problem, most of them consider the classification between different UAV models. Classification between drones of the same model has not yet fully been investigated. In this work, we consider the tasks of detecting and localizing UAV signals in a wideband spectrum, and also the task of fingerprinting these drones of the same model simultaneously. To solve this problem, we collect the UAVSig, an over-the-air dataset of UAV RF signals. We also present a deep learning model which can solve detect and fingerprint multiple drones of the same model simultaneously based on spectrograms. Our model can achieve 99.5% precision and 99.4% recall for transmission detection, and 90.9% classification accuracy with drones of the same model.

ABSTRACTAs society becomes more reliant on machines and automation, understanding how people utilize advice is a necessary endeavor. Our objective was to reveal the underlying neural associations during advice utilization from expert human and machine agents with fMRI and multivariate Granger causality analysis. During an X-ray luggage-screening task, participants accepted or rejected good or bad advice from either the human or machine agent framed as experts with manipulated reliability (high miss rate). We showed that the machine-agent group decreased their advice utilization compared to the human-agent group and these differences in behaviors during advice utilization could be accounted for by high expectations of reliable advice and changes in attention allocation due to miss errors. Brain areas involved with the salience and mentalizing networks, as well as sensory processing involved with attention, were recruited during the task and the advice utilization network consisted of attentional modulation of sensory information with the lingual gyrus as the driver during the decision phase and the fusiform gyrus as the driver during the feedback phase. Our findings expand on the existing literature by showing that misses degrade advice utilization, which is represented in a neural network involving salience detection and self-processing with perceptual integration.

The Stress Resilience Training System (SRTS®) is a new game-based learning application for tablets that trains users to better control stress through interactive education and advanced biofeedback. The goal of using the application is to allow users to better manage the positive and negative effects of stress. The application is targeted at young soldiers who may be more technologically- and game-motivated. An initial usability study with SRTS was conducted to determine its effectiveness and ease of use. A unique application of the link analysis method combined with retrospective probing revealed that users were following coach recommendations, but skipped vital information necessary to play the games. Results further showed that users with high subjective resilience were likely to find the application useful. Link analysis can help analyze exploratory learning behavior and relevant external comparison measures can inform future use of a product.

The proliferation of unmanned aerial vehicles (UAVs) in civil and military domains has spurred increasingly complex automation design for augmenting operator abilities, reducing workload, and increasing mission effectiveness. We describe the Adaptive Interface Management System (AIMS), an intelligent adaptive delegation interface for controlling and monitoring multiple unmanned vehicles, with a mixed-initiative team model language. A study was conducted to assess understanding of this model language and whether participants exhibited calibrated trust in the intelligent automation. Results showed that operators had accurate memory for role responsibility and were well calibrated to the automation. Adaptive automation design approaches like the one described in this paper can be useful to create mixedinitiative human-robot teams.

This paper presents a team plan specification language that combines work in the creation of generic team plans and design of intelligent interfaces. Two key motivations for developing the language are (1) to combine inter-agent cooperation and operator interaction of complex behaviors into a single plan, and (2) to separate plan design and UI design such that they are created by application domain experts and human interaction experts, respectively. The presented result is a generic language for multi-robot plans that defines tasks to be performed, operator interactions for maintaining situational awareness, and mixed initiative actions to react to operator workload.

This paper describes a new software system that is designed to facilitate the cognitive processes of the operational planning team in counterinsurgency (COIN) environments. COIN environments pose many cognitive challenges to the operational planner; planners must maintain situation awareness, reason with numerous factors in the decision making process, and coordinate actions across echelons to ensure that long term goals are being met. The software system, called the Decision Infrastructure for Counterinsurgency Operational Planning (DICOP), provides an analytical framework for the operational planner that meets many of the cognitive challenges faced by the planning staff. DICOP provides a method for organizing and tracking relevant situational data, visualizing and modeling operational factors to facilitate decision making, and identifying and planning courses of action. These methods for improving cognitive effectiveness and the current field evaluation of DICOP in Iraq are discussed. Language: en