Advancements in deep neural networks have contributed to near-perfect results for many computer vision problems, such as object recognition, face recognition, and pose estimation. However, human action recognition is still far from human-level performance. Owing to the articulated nature of the human body, it is challenging to detect an action from multiple viewpoints, particularly from an aerial viewpoint. This is further compounded by a scarcity of datasets that cover multiple viewpoints of actions. To fill this gap and enable research in wider application areas, in this article we present a multiviewpoint outdoor action recognition dataset collected from YouTube and our own drone. The dataset consists of 20 dynamic human action classes, 2324 video clips, and 503 086 frames. All videos are cropped and resized to 720 × 720 without distorting the original aspect ratio of the human subjects in videos. This dataset should be useful to many research areas, including action recognition, surveillance, and situational awareness. We evaluate the dataset with a two-stream convolutional neural network architecture coupled with a recently proposed temporal pooling scheme called kernelized rank pooling that produces nonlinear feature subspace representations. The overall baseline action recognition accuracy is 74.0%.

Many drone platforms have matured to become nearly optimal flying machines with only modest improvements in efficiency possible. “Chimera” craft combine fixed wing and rotary wing characteristics while being substantially less efficient than both. The increasing presence of chimeras suggests that their mix of vertical takeoff, hover, and more efficient cruise is invaluable to many end users. We discuss the opportunity for flapping wing drones inspired by large insects to perform these mixed missions. Dragonflies particularly are capable of efficiency in all modes of flight. We will explore the fundamental principles of dragonfly flight to allow for a comparison between proposed flapping wing technological solutions and a flapping wing organism. We chart one approach to achieving the next step in drone technology through systems theory and an appreciation of how biomimetics can be applied. New findings in dynamics of flapping, practical actuation technology, wing design, and flight control are presented and connected. We show that a theoretical understanding of flight systems and an appreciation of the detail of biological implementations may be key to achieving an outcome that matches the performance of natural systems. We assert that an optimal flapping wing drone, capable of efficiency in all modes of flight with high performance upon demand, might look somewhat like an abstract dragonfly.

The World Health Organization (WHO) has declared COVID-19 a pandemic. We review and reduce the clinical literature on diagnosis of COVID-19 through symptoms that might be remotely detected as of early May 2020. Vital signs associated with respiratory distress and fever, coughing, and visible infections have been reported. Fever screening by temperature monitoring is currently popular. However, improved noncontact detection is sought. Vital signs including heart rate and respiratory rate are affected by the condition. Cough, fatigue, and visible infections are also reported as common symptoms. There are non-contact methods for measuring vital signs remotely that have been shown to have acceptable accuracy, reliability, and practicality in some settings. Each has its pros and cons and may perform well in some challenges but be inadequate in others. Our review shows that visible spectrum and thermal spectrum cameras offer the best options for truly noncontact sensing of those studied to date, thermal cameras due to their potential to measure all likely symptoms on a single camera, especially temperature, and video cameras due to their availability, cost, adaptability, and compatibility. Substantial supply chain disruptions during the pandemic and the widespread nature of the problem means that cost-effectiveness and availability are important considerations.

This research investigates the use of a Linear Quadratic Regulator (LQR) controller to assist commercial Boeing 747-200 aircraft regains its stability in the event of damage. Damages cause an aircraft to become asymmetric and in the case of damage to a fraction (33%) of its left wing or complete loss of its vertical stabilizer, the loss of stability may lead to a fatal crash. In this study, aircraft models for the two damage scenarios previously mentioned are constructed using stability derivatives. LQR controller is used as a direct adaptive control design technique for the observable and controllable system. Dynamic stability analysis is conducted in the time domain for all systems in this study.

Insects use dynamic articulation and actuation of their abdomen and other appendages to augment aerodynamic flight control. These dynamic phenomena in flight serve many purposes, including maintaining balance, enhancing stability, and extending maneuverability. The behaviors have been observed and measured by biologists but have not been well modeled in a flight dynamics framework. Biological appendages are generally comparatively large, actuated in rotation, and serve multiple biological functions. Technological moving masses for flight control have tended to be compact, translational, internally mounted and dedicated to the task. Many flight characteristics of biological flyers far exceed any technological flyers on the same scale. Mathematical tools that support modern control techniques to explore and manage these actuator functions may unlock new opportunities to achieve agility. The compact tensor model of multibody aircraft flight dynamics developed here allows unified dynamic and aerodynamic simulation and control of bioinspired aircraft with wings and any number of idealized appendage masses. The demonstrated aircraft model was a dragonfly-like fixed-wing aircraft. The control effect of the moving abdomen was comparable to the control surfaces, with lateral abdominal motion substituting for an aerodynamic rudder to achieve coordinated turns. Vertical fuselage motion achieved the same effect as an elevator, and included potentially useful transient torque reactions both up and down. The best performance was achieved when both moving masses and control surfaces were employed in the control solution. An aircraft with fuselage actuation combined with conventional control surfaces could be managed with a modern optimal controller designed using the multibody flight dynamics model presented here.

Electrical insulation failure is the most common failure mechanism in electrical machines (motors and generators). High temperatures and/or temperature gradients (HTTG) are the main drivers of insulation failure in electrical machines. HTTG combine with and augment other destructive effects from over-voltage, to voltage transients, overload and load variations, poor construction techniques, and thermal cycling. These operating conditions cause insulation damage that leads to electrical insulation failure. The insulation failure process is greatly accelerated by pollutants and moisture absorption. A simple and robust way to reduce HTTG and moisture adsorption is by maintaining constant internal temperatures. The current method to maintain elevated internal temperatures and reduce condensation issues is by internal electrical heating elements. This paper examines the effectiveness of applying thermoelectric coolers (TECs), solid-state heat pumps (Peltier devices), as heaters to raise a motor’s internal temperature by pumping heat into the motor core rather than heating the internal air. TEC technology is relatively new, and the application of TECs to heat a motor’s internal volume has not previously been explored. In this paper, we explore the hypothesis that TECs can pump heat into a motor when out of service, reducing the HTTG by maintaining high winding slot temperatures and eliminating condensation issues. This paper describes a test motor setup with simple resistive heating (traditional method), compared with the application of TECs with heat sinks, heat pipes, and a water circulation heat exchanger, to gauge the capability of TECs to heat the inner core or winding area. In this paper, we demonstrate the full integration of TECs into a motor. The results show that each of the systems incorporating the TECs would effectively pump heat into the core and keep the winding hot, eliminating condensation issues and water ingress due to thermal cycling.