Hovering recognition by ADS-B data mining

Recently, artificial intelligence and data science have witnessed dramatic progress and rapid growth, especially Automatic Speech Recognition (ASR) technology based on Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs). Consequently, new end-to-end Recurrent Neural Network (RNN) toolkits were developed with higher speed and accuracy that can often achieve a Word Error Rate (WER) below 10%. These toolkits can nowadays be deployed, for instance, within aircraft cockpits and Air Traffic Control (ATC) systems in order to identify aircraft and display recognized voice messages related to flight data, especially for airports not equipped with radar. Hence, the performance of air traffic controllers and pilots can ultimately be improved by reducing workload and stress and enforcing safety standards. Our experiment conducted at Tangier’s International Airport ATC aimed to build an ASR model that is able to recognize aircraft call signs in a fast and accurate way. The acoustic and linguistic models were trained on the Ibn Battouta Speech Corpus (IBSC), resulting in an unprecedented speech dataset with approved transcription that includes real weather aerodrome observation data and flight information with a call sign captured by an ADS-B receiver. All of these data were synchronized with voice recordings in a structured format. We calculated the WER to evaluate the model’s accuracy and compared different methods of dataset training for model building and adaptation. Despite the high interference in the VHF radio communication channel and fast-speaking conditions that increased the WER level to 20%, our standalone and low-cost ASR system with a trained RNN model, supported by the Deep Speech toolkit, was able to achieve call sign detection rate scores up to 96% in air traffic controller messages and 90% in pilot messages while displaying related flight information from ADS-B data using the Fuzzy string-matching algorithm.

The use of a GIS-based malaria information system for malaria research and control in South Africa

As the markets for unmanned aerial vehicles (UAVs) and mixed reality (MR) headsets continue to grow, recent research has increasingly explored their integration, which enables more intuitive, immersive, and situationally aware control systems. We present IGUANA, an MR-based immersive guidance, navigation, and control system for consumer UAVs. IGUANA introduces three key elements beyond conventional control interfaces: (1) a 3D terrain map interface with draggable waypoint markers and live camera preview for high-level control, (2) a novel spatial control metaphor that uses a virtual ball as a physical analogy for low-level control, and (3) a spatial overlay that helps track the UAV when it is not visible with the naked eye or visual line of sight is interrupted. We conducted a user study to evaluate our design, both quantitatively and qualitatively, and found that (1) the 3D map interface is intuitive and easy to use, relieving users from manual control and suggesting improved accuracy and consistency with lower perceived workload relative to conventional dual-stick controller, (2) the virtual ball interface is intuitive but limited by the lack of physical feedback, and (3) the spatial overlay is very useful in enhancing the users' situational awareness.

Recent work into quantifying the impact of attacks on control systems has motivated the design of worst-case attacks that define the envelope of the attack impact possible while remaining stealthy to model-based anomaly detectors. Such attacks - although stealthy for the considered detector test - tend to produce detector statistics that are easily identifiable by the naked eye. Although seemingly obvious, human operators cannot simultaneously monitor all process control variables of a large-scale cyber-physical system. What is lacking in the literature is a set of practical detectors that can identify such unusual attacked behavior. In defining these, we enable automated detection of to-date stealthy attacks and also further constrain the impact of attacks stealthy to a set of combined detectors, both existing and new.

PurposePrior literature provides little insight on how management control systems have responded to the growth of collaborative new product development (NPD). The purpose of this paper is to contrast the use of budgets to manage collaborative and in-house NPD and to consider the implications for enabling flexibility.Design/methodology/approachThe paper reports on the findings of a case study company in the medical devices industry that uses two different business models for its NPD activities. While the company engages in in-house NPD for its own products, it also engages in collaborative NPD services with a range of customers.FindingsThe study illuminates how two types of budgets (annual and project) can have very different impacts on flexibility under different business models. The annual financial budgets imposed rigid constraints on in-house NPD and resulted in reduced flexibility, whereas in collaborative NPD, they had little impact on flexibility. Project budgets created hard operational constraints in collaborative NPD which generated a highly pressurised yet highly creative environment, whereas project budgets had little impact on flexibility in in-house NPD.Originality/valueThe study contributes detailed empirical insights into the control systems used to manage collaborative NPD from the supplier perspective, where creativity is largely responsive and contrasts these with the management of in-house NPD where creativity is largely expected. The authors also contribute an analysis of the key control systems and other factors that sustain flexibility in this highly pressurised open innovation environment.

A method to monitor New Zealand's native bees using image processing technology is presented. Since most species are solitary ground nesting bees the number of active nests within an area can give a good estimate of the population of a community. The number of native bees in flight around plants can also provide valuable information about the overall health of a community and help to quantify their value in the ecosystem as keystone pollinators. On this basis, images of insects in flight have been collected across one season and the results compared with previous results of active nest counts. Open source software FIJI was used to pre-process and classify images. Accuracies were verified using data mining software WEKA. Performance evaluations showed the fast random forest classifier consistently returned fast, accurate results. Fine differences in images were discriminated that were otherwise impossible to identify with the naked eye and even when training data were unevenly distributed the classifier returned accuracies above 98%. The results are promising and while there are few alternatives to traditional methods, image processing for ecology can provide cost effective, standardized tools to help monitor the population and diversity of native bees in New Zealand.

En muchas universidades mexicanas, grupos de profesores conforman cuerpos académicos con la finalidad de generar nuevos conocimientos con base en la colaboración de sus miembros. Estos cuerpos académicos son clasificados siguiendo criterios establecidos por el Programa para el Desarrollo Profesional Docente (Prodep). Sin embargo, su valoración puede resultar subjetiva por la ausencia de herramientas que faciliten dicho proceso. Este trabajo se enfocó en analizar la producción y la colaboración de tres tipos de cuerpos académicos a partir de la información almacenada en la base de datos Scopus, haciendo uso de la visualización de datos, aplicando la teoría de grafos. La metodología utilizada se basa en la minería de datos educativos. Los resultados permitieron observar una correspondencia entre la estructura del grupo y el cumplimiento de la producción solicitada por el Prodep; los elementos más fuertes y más débiles de cada cuerpo académico fueron localizados con base en su participación y nivel de contribución. El aporte de esta investigación es el análisis de la producción y colaboración científica de un cuerpo académico haciendo uso de la teoría de grafos, lo que permite automatizar el proceso de evaluación y, de esta manera, reducir su interpretación subjetiva.

<i>Heterodera glycines:</i> procedures for official control

The advantages of using collaborative and distributed systems to control and optimise industrial environments have been explored in recent years. However, the self-organised and dynamic approaches that deliver these same advantages bring challenges associated with the long-term unpredictability of these approaches. The proposed work aims to present a framework that integrates a Digital Twin-based Optimiser within these systems to predict the system's evolution and reconfigure it if required. Digital Twins can be an essential advantage in adopting these systems due to the possibility of carrying out simulations at an accelerated speed and reconfiguring the self-organised control system.

The ground test environment is established for rapid development and raising high operational reliability of micro-satellites. It aims to verify the attitude determination and control system (ADCS) in hardware-in-the-loop simulation. In this research, the performance of simulator is improved and verified based on flight data of real satellite. Space Robotics Laboratory (SRL) of Tohoku University has developed two 50-kg-class micro-satellites. Due to a short development term, the ground verification environment is required for supporting rapid development of ADCS. SRL established a Model-based Environment for Verification and Integration of μ-Satellites called “MEVIμS”, which works as a hardware-in-the-loop simulator to evaluate real satellite hardware on ground. Due to its versatility, it can apply for other satellites. The flight data obtained from Philippines' micro-satellite called “DIWATA-1” which is currently working for remote sensing over Philippines are analyzed on ground. Then, orbit and attitude dynamics calculators implemented on the simulator are improved and verified based on its flight data. The results demonstrate that dynamics calculators are authentic and this system is practical to conduct ADCS evaluation in static closed loop simulation.

Quadrotor is widely used in variable application nowadays. Due to its inherent unstable characteristics, control system to augment the stability is essential for quadrotor operation. To design control system and verify its performance through simulation, accurate dynamic model is required. Quadrotor dynamic model is simply compared with conventional rotorcraft such as helicopter. However, the accurate dynamic model of quadrotor is not easy to develop because of the highly correlated aerodynamic effect of each rotor. In this paper, quadrotor dynamic model is identified from the flight data using frequency domain approach. Flight test of quadrotor is performed in closed loop configuration with stability augmentation system included. Frequency sweep input is applied in each of lateral, longitudinal, yaw and heave axis separately. The bare dynamic model is identified from the flight data of quadrotor responses and thrust measurement through Pulse Width Modulation(PWM) data. The frequency responses of identified model match well with those of flight data, and time responses of identified model for doublet input in each axis are also shown to agree with flight data.

Singular value analysis can give conservative stability margin results. Applying structure to the uncertainty can reduce this conservatism. This paper presents flight-determined stability margins for the X-29A lateral-directional, multiloop control system. These margins are compared with the predicted unscaled singular values and scaled structured singular values. The algorithm was further evaluated with flight data by changing the roll-rate-to-aileron command-feedback gain by +/- 20 percent. Minimum eigenvalues of the return difference matrix which bound the singular values are also presented. Extracting multiloop singular values from flight data and analyzing the feedback gain variations validates this technique as a measure of robustness. This analysis can be used for near-real-time flight monitoring and safety testing.

This paper describes a low-cost flight control system of a small aileron-less hand-launched solar-powered unmanned aerial vehicle (UAV). In order to improve the accuracy of the whole system model and quantify the influence of each subsystem, detailed modeling of UAV energy and a control system including a solar model, engine, energy storage, sensors, state estimation, control law, and actuator module are established in accordance with the experiment and component principles. A whole system numerical simulation combined with the 6 degree-of-freedom (DOF) simulation model is constructed based on the typical mission route, and the parameter precision sequence and energy balance are obtained. Then, a hardware-in-the-loop (HIL) experiment scheme based on the Stewart platform (SP) is proposed, and three modes of acceleration, angular velocity, and attitude are designed to verify the control system through the inner and boundary states of the flight envelope. The whole system scheme is verified by flight tests at different altitudes, and the aerodynamic force coefficient and sensor error are corrected by flight data. With the increase of altitude, the cruise power increases from 47 W to 78 W, the trajectory tracking precision increases from 23 m to 44 m, the sensor measurement noise increases, and the bias decreases.

Correct determination of target class in Air Defense Systems is important for fire doctrine that will be used against the targets that are identified as threat in decision support systems. In this study, performance of different machine learning classification algorithms that utilize not only observable flight performance features but also Radar Cross Section (RCS) feature that is observed by the radar are compared against each other. In order to utilize the proposed classification algorithm, a method is proposed for creating a threat database utilizing open ADS-B data using data mining techniques.

Approach and landing are among the most challenging and dangerous tasks required of helicopter pilots. Helicopter accident statistics suggest that the majority of helicopter accidents occur during the approach and landing phases of flight. Unstabilized approaches are a leading cause of these accidents due to the increased potential for loss of control, loss of situational awareness, or controlled flight into terrain. In the present work, routine flight data records obtained as part of a voluntary helicopter flight data monitoring program are used to identify, analyze, and evaluate the stability of instrument approach events. A data fusion process is developed that enables detection of the approach phase, identification of an associated instrument approach procedure, analysis of approach stability, and knowledge discovery through data mining. The process identified 385 instrument approach events in a set of 7063 operational helicopter flight data records. Manual analysis of these events reveals some common errors, including crossing the final approach fix far below the assigned altitude and violating the minimum altitude requirement during initial and intermediate approach legs and course reversal maneuvers. Data mining algorithms are tested and found to be capable of automatically identifying atypical or unstable approach events.