Multi-Frequency Radar Micro-Doppler Based Classification of Micro-Drone Payload Weight

Dhulashia, Dilan; Peters, Nial; Horne, Colin; Beasley, Piers J.; Ritchie, Matthew

doi:10.3389/frsip.2021.781777

Cited by 13 publications

(14 citation statements)

References 19 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gradient Vanishing occurs when the number of layers increases, the gradient of the loss function decreases, and at some point, it becomes zero. As shown in Figure (5), the LSTM cell consists of three parts: forget gate, input gate, and output gate. The forget gate decides to store the information coming from the previous timestamp or to forget it.…”

Section: Long Short-term Memory Network (Lstm)mentioning

confidence: 99%

“…Classification of payload weight of microdrone was presented in this work [5] by using micro-Doppler signatures data from a radar that operated on three different frequency bands; S-band, C-band, and W-band. The data set belonged to two different types of micro-drone with three distinguished payloads; they also had two different motion styles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Payload Prediction for Quadro Drone using Temporal Deep Machine Learning Models

Zitar,

Kashkash,

Seghrouchni

et al. 2024

Preprint

View full text Add to dashboard Cite

In this paper, four different deep-learning and temporal machine-learning techniques are used to predict the payload of the DJI Matrice 100 quadcopter drone based on its tracking data. Tracking variables for real-life experimentations are provided as open source for payloads of 0.0, 250, 500, and 750 grams. The drone is a Quado drone DJI matrice 100. The Machine Learning techniques are RNN, LSTM, TCN, and GRU. The values of the tracks’ kinematics come from several different flights for the different loads. The tracks’ kinematics and flight parameters are used in training the four models. The temporal nature of the data values triggers the need for machine learning methods that use history/memory as part of inputs. This application is a real and relevant test to evaluate the capabilities of the 4 famous types of deep temporal machine learning models. The original data has more than 1400 records for every flight with more than 22 variable values. More than 270 flights were conducted with the 4 payloads. The models were tuned and initialized with the optimum parameters found. Several simulations were implemented for training, testing, and validation. Cross-validation for the models was implemented The RMSE and MAE errors were used to evaluate the loss and the accuracies. The TCN model with the optimum parameters showed the best performance compared to other techniques. The RNN (many-to-one) showed the lowest performance. The results emphasize the superiority of the modern TCN methods over other temporal deep techniques for this kind of problem.

show abstract

Section: Long Short-term Memory Network (Lstm)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Payload Prediction for Quadro Drone using Temporal Deep Machine Learning Models

Zitar,

Kashkash,

Seghrouchni

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…As illustrated in Figure 13 ARESTOR uses the ZCU111 RFSoC evaluation board as its fundamental building block, and created a suite of custom hardware (e.g. Figure 14), software and FPGA configurations for it which enable transmit and receive on multiple channels, across different frequency bands, in a multistatic arrangement that can also use different sensing modes (Active Radar [42]/Passive Radar [37]/Joint Radar‐comms. [43]).…”

Section: Arestor Multistatic Radar System Synchronisationmentioning

confidence: 99%

Global Navigation Satellite Systems disciplined oscillator synchronisation of multistatic radar

Beasley,

Peters,

Horne

et al. 2023

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

A fundamental challenge in the practical implementation of multistatic radar systems (MSRS) is the requirement for precise time and frequency synchronisation between the spatially separated radar nodes. The authors evaluate the performance of different classes of commercially available Global Navigation Satellite Systems (GNSS) timing receivers, Local Oscillators (LO) and GNSS Disciplined Oscillators (GNSSDOs) to determine the limitations of using one‐way GNSS Time and Frequency Transfer (TFT) in this application. From evaluating the performance of three pairs of GNSSDOs, it is concluded that one‐way GNSS TFT will likely be suitable only for the synchronisation of fully spatially coherent MSRS with carrier frequencies up to 100 MHz and waveform bandwidths up to 20 MHz. Whereas, in the case of short‐term spatially coherent MSRS, synchronisation of systems with carrier frequencies up to a few GHz and waveform bandwidths of over 100 MHz will likely be possible. The performance of the different classes of GNSSDOs during GNSS denial (holdover) are evaluated, where it is concluded that frequency offsets between LOs at the point of GNSS denial will often significantly contribute, or even dominate, the holdover performance. Analysis of two practical multistatic radar measurements verifies the function of using the GNSSDOs for wireless synchronisation of the ARESTOR MSRS.

show abstract

“…These building blocks are combined, configured and built into different system solutions by a combination of TCL and Python scripting based on a high-level design specification file. Examples of the solutions created are a frequency modulated continuous wave (FMCW) radar, an FMCW radar capable of capturing full polarisation information, a multi-band FMCW radar operating in ISM bands at 2.4 GHz and 5.8 GHz [33], an active-passive radar featuring simultaneous capture of target returns from an FMCW active radar and a WiFi illuminator based passive radar [34], and a dual-function radar and communication (DFRC) device [35].…”

Section: Experimental Hardware and Configuration A The Arestor Rf Pla...mentioning

confidence: 99%

Classification of LoRa Signals With Real-Time Validation Using the Xilinx Radio Frequency System-on-Chip

2023

View full text Add to dashboard Cite

This paper demonstrates a real-time LoRa Internet of Things (IoT) signal classification technique that runs on Xilinx Radio Frequency System-on-Chip (RFSoC) hardware. IoT signals are being used for wider arrays of applications and therefore awareness of their presence is important for cyber security and infrastructure protection as well as battlefield situational awareness. Within this research a dataset of LoRa waveforms is captured using the RFSoC which bounds the possible combinations of waveform parameters. Offline algorithms are tested against this data to evaluate how to extract the centre frequency, bandwidth and spreading factor. The algorithms are then adapted to run natively on the Xilinx RFSoC itself to enable real-time classification of waveforms from non-cooperative LoRa transmitters with a high degree of classification success.

show abstract

Multi-Frequency Radar Micro-Doppler Based Classification of Micro-Drone Payload Weight

Cited by 13 publications

References 19 publications

Payload Prediction for Quadro Drone using Temporal Deep Machine Learning Models

Payload Prediction for Quadro Drone using Temporal Deep Machine Learning Models

Global Navigation Satellite Systems disciplined oscillator synchronisation of multistatic radar

Classification of LoRa Signals With Real-Time Validation Using the Xilinx Radio Frequency System-on-Chip

Contact Info

Product

Resources

About