Search

Automated Foreign Object Debris (FOD) detection offers significant benefit to the aviation industry by reducing human error and enabling continuous surveillance. This paper focuses on addressing the intricacies of FOD detection, with a specific emphasis on treating FODs as "small" objects, a facet which has received limited attention in prior research. This study provides a pioneering evaluation of state-of-the-art object detectors, including both anchor-based models including SSD, YOLOv5m, Scaled YOLOv4 and anchorless models CenterNet and YOLOv8m, applied to a multiclass FOD dataset, "FOD in Airports (FOD-A)", as well as meticulously curated subset of FOD-A featuring small FODs. The findings reveal that the anchorless object detector YOLOv8m gives the best time accuracy trade off outperforming all compared anchor-based and anchorless approaches. To address the challenge of detecting small FODs, this study optimizes YOLOv8m model by making architectural modifications and incorporating a dedicated, shallow detection head that is purpose-built for the precise identification of small objects. The proposed model, termed as "Improved YOLOv8", outperforms YOLOv8m by a margin of 1.02 in Average Precision for small objects (APs), achieving a mean average precision (mAP) of 93.8%. Notably, Improved YOLOv8 also has better mAP than all the considered anchor-based and anchorless object detectors examined, as well as those featured in prior FOD-A dataset research. [ABSTRACT FROM AUTHOR]

Various noise effects do usually degrade the back-reflected signals of the phase-sensitive optical time-domain reflectometry (ϕ -OTDR) systems. All the induced noise effects in these signals are known to have similar effects to date and therefore, it was impossible to segregate the noise effects. A study regarding the segregation of trace-to-trace fluctuation (TTF) noise in ϕ -OTDR systems is important as it can open doors for noise mitigation in these systems. Moreover, a division of these noise effects into two parts is possible with the help of their characteristics. To do so, one of these noise effects can be characterized as a spatially variable noise (SVN), which is a dominant noise effect within a direct detected ϕ -OTDR system, whereas the second type of noise effect can be characterized as a spatially constant noise (SCN), whose effect is found in both direct and coherent detected ϕ -OTDR systems. These harmful noise effects are characterized in this work by the matched filtering moving (MFM) algorithm. Therefore, we consider that this characterization can be proved as the first step for noise mitigation in ϕ -OTDR systems. [ABSTRACT FROM AUTHOR]

Determination of whether or not the electroencephalography (EEG) ambient signal is Gaussian-distributed is important for a variety of engineering applications, such as cognitive studies and cortical source localization, as well as for a theoretical understanding of the brain’s physiology. The statistical normality of EEG ambient signals has variably been affirmed/negated in the research literature. Therefore, in light of the evolving applications of EEG, one prime objective of this work is to statistically characterize the baseline EEG signal obtained from healthy subjects to be used as a reference in future studies that involve EEG signals. In addition, this present work will critically examine the alleged normality trend by introducing more appropriately rigorous statistical techniques to reveal/characterize the statistical normality of EEG datasets. Then, this work will apply these statistical tools quantitatively to a dataset collected from healthy subjects using high-density EEG recordings with over an order-of-magnitude more electrodes compared to previously reported works. The analysis results show that the maximal data-observation duration is found to be at most 0.2 seconds for a normality-test positivity rate of 98%; for 95%, 90%, 85%, and 80%, the respective ceilings can relax, respectively, to 0.3, 1.0, 1.6, and 2.9 seconds. [ABSTRACT FROM AUTHOR]

With the deployment of radar in versatile scenarios and a wide variety of potential targets, demand for automatic classification of various targets is increasing. The wide variety of radar signatures from physically smaller targets due to lower velocity / radar cross-section thresholds and the increased deployment of radar-based sensors do crowd the radar screen with misinterpreted targets. Micro-Doppler signatures have been widely employed by researchers for the recognition of those targets that exhibit micro-motions. This review article presents the evolution and recent advances in radar micro-Doppler based signature analysis and feature extraction. A review of the micro-Doppler-based target classification techniques along with their applications in defense and commercial sectors, has also been presented. This article provides the first review paper in the open literature that systematically covers the major steps along with the adopted practices in micro-Doppler based target recognition. Moreover, the limitations and future trends in the field are also discussed. [ABSTRACT FROM AUTHOR]

A “p-u probe” (also known as a “p-v probe”) comprises one pressure-sensor (which is isotropic) and one uni-axial particle-velocity sensor (which has a “figure-8” bi-directional spatial directivity). This p-u probe may be generalized, by allowing the figure-8 bi-directional sensor to have a higher order of directivity. This higher-order p-u probe has not previously been investigated anywhere in the open literature (to the best knowledge of the present authors). For such a sensing system, this paper is first (1) to develop closed-form eigen-based signal-processing algorithms for azimuth-elevation direction finding; (2) to analytically derive the associated Cramér-Rao lower bounds (CRB), which are expressed explicitly in terms of the two constituent sensors' spatial geometry and in terms of the figure-8 sensor's directivity order; (3) to verify (via Monte Carlo simulations) the proposed direction-of-arrival estimators' efficacy and closeness to the respective CRB. Here, the higher-order p-u probe's two constituent sensors may be spatially displaced. [ABSTRACT FROM AUTHOR]

The concept of the cloud-to-thing continuum addresses advancements made possible by the widespread adoption of cloud, edge, and IoT resources. It opens the possibility of combining classical symbolic AI with advanced machine learning approaches in a meaningful way. In this paper, we present a thing registry and an agent-based orchestration framework, which we combine to support semantic orchestration of IoT use cases across several federated cloud environments. We use the concept of virtual sensors based on machine learning (ML) services as abstraction, mediating between the instance level and the semantic level. We present examples of virtual sensors based on ML models for activity recognition and describe an approach to remedy the problem of missing or scarce training data. We illustrate the approach with a use case from an assisted living scenario. [ABSTRACT FROM AUTHOR]