Machine Learning Verification and Safety for Unmanned Aircraft - A Literature Study

2022 ◽  
Author(s):  
Christoph Torens ◽  
Franz Juenger ◽  
Sebastian Schirmer ◽  
Simon Schopferer ◽  
Theresa D. Maienschein ◽  
...  
Keyword(s):  
Machine Learning ◽  
Unmanned Aircraft ◽  
Literature Study

scholarly journals An Automated Machine Learning Framework in Unmanned Aircraft Systems: New Insights into Agricultural Management Practices Recognition Approaches

2021 ◽  
Vol 13 (16) ◽  
pp. 3190
Author(s):  
Kai-Yun Li ◽  
Niall G. Burnside ◽  
Raul Sampaio de Lima ◽  
Miguel Villoslada Peciña ◽  
Karli Sepp ◽  
...  
Keyword(s):  
Machine Learning ◽  
Classification Accuracy ◽  
Management Practices ◽  
Agricultural Management ◽  
Unmanned Aircraft ◽  
Unmanned Aircraft Systems ◽  
Support Vector ◽  
Diverse Range ◽  
Aircraft Systems ◽  
Automated Machine Learning

The recent trend of automated machine learning (AutoML) has been driving further significant technological innovation in the application of artificial intelligence from its automated algorithm selection and hyperparameter optimization of the deployable pipeline model for unraveling substance problems. However, a current knowledge gap lies in the integration of AutoML technology and unmanned aircraft systems (UAS) within image-based data classification tasks. Therefore, we employed a state-of-the-art (SOTA) and completely open-source AutoML framework, Auto-sklearn, which was constructed based on one of the most widely used ML systems: Scikit-learn. It was combined with two novel AutoML visualization tools to focus particularly on the recognition and adoption of UAS-derived multispectral vegetation indices (VI) data across a diverse range of agricultural management practices (AMP). These include soil tillage methods (STM), cultivation methods (CM), and manure application (MA), and are under the four-crop combination fields (i.e., red clover-grass mixture, spring wheat, pea-oat mixture, and spring barley). Furthermore, they have currently not been efficiently examined and accessible parameters in UAS applications are absent for them. We conducted the comparison of AutoML performance using three other common machine learning classifiers, namely Random Forest (RF), support vector machine (SVM), and artificial neural network (ANN). The results showed AutoML achieved the highest overall classification accuracy numbers after 1200 s of calculation. RF yielded the second-best classification accuracy, and SVM and ANN were revealed to be less capable among some of the given datasets. Regarding the classification of AMPs, the best recognized period for data capture occurred in the crop vegetative growth stage (in May). The results demonstrated that CM yielded the best performance in terms of classification, followed by MA and STM. Our framework presents new insights into plant–environment interactions with capable classification capabilities. It further illustrated the automatic system would become an important tool in furthering the understanding for future sustainable smart farming and field-based crop phenotyping research across a diverse range of agricultural environmental assessment and management applications.

scholarly journals Advances in Soil Moisture Retrieval from Multispectral Remote Sensing Using Unmanned Aircraft Systems and Machine Learning Techniques

2020 ◽  
Author(s):  
Samuel N. Araya ◽  
Anna Fryjoff-Hung ◽  
Andreas Anderson ◽  
Joshua H. Viers ◽  
Teamrat A. Ghezzehei
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Soil Moisture ◽  
High Resolution ◽  
Environmental Modeling ◽  
Unmanned Aircraft ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Boosted Regression Tree ◽  
Terrain Attributes

Abstract. We developed machine learning models to retrieve surface soil moisture (0–4 cm) from high resolution multispectral imagery using terrain attributes and local climate covariates. Using a small unmanned aircraft system (UAS) equipped with a multispectral sensor we captured high resolution imagery in part to create a high-resolution digital elevation model (DEM) as well as quantify relative vegetation photosynthetic status. We tested four different machine learning algorithms. The boosted regression tree algorithm gave the best prediction with mean absolute error of 3.8 % volumetric water content. The most important variables for the prediction of soil moisture were precipitation, reflectance in the red wavelengths, potential evapotranspiration, and topographic position indices (TPI). Our results demonstrate that the dynamics of soil water status across heterogeneous terrain may be adequately described and predicted by UAS remote sensing data and machine learning. Our modeling approach and the variable importance and relationships we have assessed in this study should be useful for management and environmental modeling tasks where spatially explicit soil moisture information is important.

scholarly journals A Practical Application of Unsupervised Machine Learning for Analyzing Plant Image Data Collected Using Unmanned Aircraft Systems

Agronomy ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 633
Author(s):  
Roy L. Davis II ◽  
Jeremy K. Greene ◽  
Fugen Dou ◽  
Young-Ki Jo ◽  
Thomas M. Chappell
Keyword(s):  
Machine Learning ◽  
Image Data ◽  
Unmanned Aircraft ◽  
Unmanned Aircraft Systems ◽  
Small Scale ◽  
Unsupervised Machine Learning ◽  
Row Crops ◽  
Aircraft Systems ◽  
Plant Nursery ◽  
Plant Pathosystems

Unmanned aircraft systems are increasingly used in data-gathering operations for precision agriculture, with compounding benefits. Analytical processing of image data remains a limitation for applications. We implement an unsupervised machine learning technique to efficiently analyze aerial image data, resulting in a robust method for estimating plant phenotypes. We test this implementation in three settings: rice fields, a plant nursery, and row crops of grain sorghum and soybeans. We find that unsupervised subpopulation description facilitates accurate plant phenotype estimation without requiring supervised classification approaches such as construction of reference data subsets using geographic positioning systems. Specifically, we apply finite mixture modeling to discern component probability distributions within mixtures, where components correspond to spatial references (for example, the ground) and measurement targets (plants). Major benefits of this approach are its robustness against ground elevational variations at either large or small scale and its proficiency in efficiently returning estimates without requiring in-field operations other than the vehicle overflight. Applications in plant pathosystems where metrics of interest are spectral instead of spatial are a promising future direction.

scholarly journals Identifikasi Hoax pada Media Sosial dengan Pendekatan Machine Learning

2018 ◽  
Vol 13 (1) ◽  
pp. 69
Author(s):  
Putu Kussa Laksana Utama
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Literature Study ◽  
Scientific Papers

<p>The Hoax propagation on social media is a problem that has to be solved. The main problem with the propagation of hoaxes on social media is that they can go viral very quickly. There have been various approaches developed to identify Hoax in the earlier stage. This study is conducted in order to analyze the various approaches that have been developed by many researchers in Hoax's identification domain. The result of literature study from various scientific papers shows that Hoax identification on social media is better if performed automatically using Machine Learning. On the several datasets, they have successfully obtain best-case accuracy of 75% -96%.</p>

scholarly journals Deteksi Objek menggunakan Dashboard Camera untuk Sistem Peringatan Pencegah Kecelakaan pada Mobil

2020 ◽  
Vol 7 (2) ◽  
pp. 427
Author(s):  
Raymond Sutjiadi ◽  
Timothy John Pattiasina
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Warning System ◽  
Video Camera ◽  
Integrated System ◽  
Advanced Technology ◽  
Problem Analysis ◽  
Literature Study ◽  
Collision Warning ◽  
Forward Collision Warning

<p>Saat ini penggunaan dashboard camera marak digunakan pada mobil untuk merekam kondisi sekitar kendaraan ketika berkendara. Dashboard camera adalah semacam kamera yang ditempatkan pada bagian dashboard mobil dengan kamera menyorot ke arah depan kendaraan yang berfungsi untuk merekam kondisi jalan. Di lain pihak, pada mobil premium saat ini sudah disematkan beberapa teknologi canggih untuk mencegah terjadinya kecelakaan atau tabrakan yang biasa disebut dengan Forward Collision Warning System. Teknologi ini pada dasarnya berfungsi untuk mencegah terjadinya tabrakan dari arah depan, baik dengan cara aktif ataupun pasif. Pada penelitian ini akan dibuat sebuah sistem terintegrasi dimana dashboard camera, yang diimplementasikan menggunakan kamera smartphone berbasis Android, tidak hanya digunakan untuk perekaman secara statis, tetapi juga digunakan untuk membuat sistem pencegah kecelakaan secara pasif. Adapun aplikasi ini dibuat dengan menggunakan metode pengolahan citra digital untuk mendeteksi keberadaan objek di depan mobil dengan menggunakan Tensorflow Open Source Machine Learning Library. Dari hasil pengujian tampak bahwa aplikasi ini mampu mendeteksi objek kendaraan berupa mobil penumpang, bus, dan truk, serta dapat memberikan peringatan baik secara visual maupun alarm apabila kendaraan di depan sudah berada pada jarak yang cukup dekat untuk memperingatkan pengemudi akan bahaya tabrakan.</p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Abstract"><em>Nowadays dashboard camera becomes familiar to be used in a car to record the condition around the vehicle while driving. Dashboard camera is a video camera placed in car’s dashboard faces in front of the vehicle to record the road condition. In the other side, premium cars now equipped with advanced technology to prevent collision called Forward Collision Warning System. This technology basically acts to prevent front collision, either in active or passive ways. In this research was built integrated system where dashboard camera, which implemented by camera of Android based smartphone, not only used as static recording, but also as passive collision avoidance system. This application was developed using Object Detection Method in Tensorflow Open Source Machine Learning Library. The research stage was started from problem analysis, literature study to search comparison from previous research, also software development and finalized with testing to measure system performance. From the testing result, this application was able to detect vehicle objects in form of passenger car, bus, and truck, also could provide both visual and alarm warning when there was a vehicle come closely from in front, to warn the driver about the danger of collision.</em></p><p><em><strong><br /></strong></em></p>

scholarly journals Li-ion Battery Aging with Hybrid Physics-Informed Neural Networks and Fleet-wide Data

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Renato G. Nascimento ◽  
Matteo Corbetta ◽  
Chetan S. Kulkarni ◽  
Felipe A. C. Viana
Keyword(s):  
Machine Learning ◽  
Computational Cost ◽  
Lithium Ion ◽  
Unmanned Aircraft ◽  
Model Parameters ◽  
Reduced Order Models ◽  
Reduced Order ◽  
Model Form ◽  
Battery Capacity ◽  
Battery Discharge

Lithium-ion batteries are commonly used to power electric unmanned aircraft vehicles (UAVs).Therefore, the ability to model both the state of charge as well as battery health is very important for reliable and affordable operation of UAV fleets.Even though models based on first principles are accurate and trustworthy, the complex electro-chemistry that governs battery discharge and aging makes it hard to build and use such models for in-time monitoring of battery conditions.Moreover, the careful tuning or estimation of high-fidelity model parameters hampers the straightforward deployment in the field.Alternatively, reduced order models have the advantage of capturing the overall behavior of battery discharge. Reduced-order principle-based models are built by carefully simplifying the physics/chemistry such that computational cost is dramatically reduced while the overall behavior of the system is still captured.These simplifications also lead to a number of parameters to be estimated based on data as well as residual discrepancy (model-form uncertainty).This approach can lead to a number of parameters to be estimated based on data as well as residual model-form uncertainty; a property shared with machine learning models. The latter are solely built on the basis of data, and can still capture unexpected nonlinearities.The drawback is that traditional machine learning tends to require large number of data points hard to retrieve in many scientific and engineering fields like, for example, the field of battery discharge and degradation prediction. In this paper, we will present a hybrid modeling approach for tracking and forecasting battery aging based on ``as-used'' conditions.Our approach directly implements a reduced-order model based on Nerst and Butler-Volmer equations within a deep neural network framework.While most of the input-output relationship is captured by reduced-order models, the data-driven kernels reduce the gap between predictions and observations.The hybrid model estimates the overall battery discharge, and a multilayer perceptron models the battery internal voltage.Battery aging is characterized by time-dependent internal resistance and the amount of available Li-ions.We address the difficult issue of building and updating the aging model by reducing the need for reference discharge cycles.This is beneficial to operators, since it reduces the need of taking the batteries out of commission.We compensate for lack of reference discharge cycles by using a probabilistic model that leverages previously available fleet-wide information. We validate our approach using data publicly available through the NASA Prognostics Center of Excellence website.Results showed that our hybrid battery prognosis model can be successfully calibrated, even with a limited number of observations.Moreover, the model can help optimizing battery operation by offering long-term forecast of battery capacity.

scholarly journals Sensor Networks for Aerospace Human-Machine Systems

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3465 ◽  
Author(s):  
Nichakorn Pongsakornsathien ◽  
Yixiang Lim ◽  
Alessandro Gardi ◽  
Samuel Hilton ◽  
Lars Planke ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sensor Networks ◽  
Operations Management ◽  
Traffic Management ◽  
Cyber Physical Systems ◽  
Unmanned Aircraft ◽  
Cognitive State ◽  
Physical Systems ◽  
Cognitive States ◽  
Machine Systems

Intelligent automation and trusted autonomy are being introduced in aerospace cyber-physical systems to support diverse tasks including data processing, decision-making, information sharing and mission execution. Due to the increasing level of integration/collaboration between humans and automation in these tasks, the operational performance of closed-loop human-machine systems can be enhanced when the machine monitors the operator’s cognitive states and adapts to them in order to maximise the effectiveness of the Human-Machine Interfaces and Interactions (HMI2). Technological developments have led to neurophysiological observations becoming a reliable methodology to evaluate the human operator’s states using a variety of wearable and remote sensors. The adoption of sensor networks can be seen as an evolution of this approach, as there are notable advantages if these sensors collect and exchange data in real-time, while their operation is controlled remotely and synchronised. This paper discusses recent advances in sensor networks for aerospace cyber-physical systems, focusing on Cognitive HMI2 (CHMI2) implementations. The key neurophysiological measurements used in this context and their relationship with the operator’s cognitive states are discussed. Suitable data analysis techniques based on machine learning and statistical inference are also presented, as these techniques allow processing both neurophysiological and operational data to obtain accurate cognitive state estimations. Lastly, to support the development of sensor networks for CHMI2 applications, the paper addresses the performance characterisation of various state-of-the-art sensors and the propagation of measurement uncertainties through a machine learning-based inference engine. Results show that a proper sensor selection and integration can support the implementation of effective human-machine systems for various challenging aerospace applications, including Air Traffic Management (ATM), commercial airliner Single-Pilot Operations (SIPO), one-to-many Unmanned Aircraft Systems (UAS), and space operations management.

Sign in / Sign up

Export Citation Format

Share Document