Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This open access book provides a wealth of hands-on examples that illustrate how hyperparameter tuning can be applied in practice and gives deep insights into the working mechanisms of machine learning (ML) and deep learning (DL) methods. The aim of the book is to equip readers with the ability to achieve better results with significantly less time, costs, effort and resources using the methods described here. The case studies presented in this book can be run on a regular desktop or notebook computer. No high-performance computing facilities are required. The idea for the book originated in a study conducted by Bartz & Bartz GmbH for the Federal Statistical Office of Germany (Destatis). Building on that study, the book is addressed to practitioners in industry as well as researchers, teachers and students in academia. The content focuses on the hyperparameter tuning of ML and DL algorithms, and is divided into two main parts: theory (Part I) and application (Part II). Essential topics covered include: a survey of important model parameters; four parameter tuning studies and one extensive global parameter tuning study; statistical analysis of the performance of ML and DL methods based on severity; and a new, consensus-ranking-based way to aggregate and analyze results from multiple algorithms. The book presents analyses of more than 30 hyperparameters from six relevant ML and DL methods, and provides source code so that users can reproduce the results. Accordingly, it serves as a handbook and textbook alike.

Artificial intelligence --- Machine learning --- Mathematical & statistical software --- Mathematical physics --- Hyperparameter Tuning --- Hyperparameters --- Tuning --- Deep Neural Networks --- Reinforcement Learning --- Machine Learning

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The emerging massive density of human-held and machine-type nodes implies larger traffic deviatiolns in the future than we are facing today. In the future, the network will be characterized by a high degree of flexibility, allowing it to adapt smoothly, autonomously, and efficiently to the quickly changing traffic demands both in time and space. This flexibility cannot be achieved when the network’s infrastructure remains static. To this end, the topic of UAVs (unmanned aerial vehicles) have enabled wireless communications, and networking has received increased attention. As mentioned above, the network must serve a massive density of nodes that can be either human-held (user devices) or machine-type nodes (sensors). If we wish to properly serve these nodes and optimize their data, a proper wireless connection is fundamental. This can be achieved by using UAV-enabled communication and networks. This Special Issue addresses the many existing issues that still exist to allow UAV-enabled wireless communications and networking to be properly rolled out.

unmanned aerial vehicle --- UAV positioning --- machine learning --- wireless communications --- drones --- network --- DTN --- mobility schedule --- routing algorithms --- data delivery --- Internet of drones --- communication --- security --- privacy --- UAV base station --- MIMO --- millimeter-wave band --- blind beamforming --- signal recovery --- UAV relay networks --- resource management --- transmit time allocation --- unmanned aerial vehicles --- dynamic spectrum access --- quality of service --- reinforcement learning --- multi-armed bandit --- aerial communication --- FANET --- not-spots --- stratospheric communication platform --- UAV --- UAV-assisted network --- 5G --- global positioning system --- GPS spoofing attacks --- detection techniques --- dynamic selection --- hyperparameter tuning --- IoT --- RF radio communication --- Wi-Fi direct --- D2D --- drone-based mobile secure zone --- friendly jamming --- mobility --- internet of things --- non-orthogonal multiple access --- resource allocation --- ultra reliable low latency communication --- uplink transmission --- Deep Q-learning (DQL) --- Double Deep Q-learning (DDQL) --- dynamic spectrum sharing --- High Altitude Platform Station (HAPS) --- cellular communications --- power control --- interference management --- cognitive UAV networks --- clustered two-stage-fusion cooperative spectrum sensing --- continuous hidden Markov model --- SNR estimation --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book focuses on the fundamental and applied research of the non-destructive estimation and diagnosis of crop leaf and plant nitrogen status and in-season nitrogen management strategies based on leaf sensors, proximal canopy sensors, unmanned aerial vehicle remote sensing, manned aerial remote sensing and satellite remote sensing technologies. Statistical and machine learning methods are used to predict plant-nitrogen-related parameters with sensor data or sensor data together with soil, landscape, weather and/or management information. Different sensing technologies or different modelling approaches are compared and evaluated. Strategies are developed to use crop sensing data for in-season nitrogen recommendations to improve nitrogen use efficiency and protect the environment.

Technology: general issues --- History of engineering & technology --- Environmental science, engineering & technology --- UAS --- multiple sensors --- vegetation index --- leaf nitrogen accumulation --- plant nitrogen accumulation --- pasture quality --- airborne hyperspectral imaging --- random forest regression --- sun-induced chlorophyll fluorescence (SIF) --- SIF yield indices --- upward --- downward --- leaf nitrogen concentration (LNC) --- wheat (Triticum aestivum L.) --- laser-induced fluorescence --- leaf nitrogen concentration --- back-propagation neural network --- principal component analysis --- fluorescence characteristics --- canopy nitrogen density --- radiative transfer model --- hyperspectral --- winter wheat --- flooded rice --- pig slurry --- aerial remote sensing --- vegetation indices --- N recommendation approach --- Mediterranean conditions --- nitrogen --- vertical distribution --- plant geometry --- remote sensing --- maize --- UAV --- multispectral imagery --- LNC --- non-parametric regression --- red-edge --- NDRE --- dynamic change model --- sigmoid curve --- grain yield prediction --- leaf chlorophyll content --- red-edge reflectance --- spectral index --- precision N fertilization --- chlorophyll meter --- NDVI --- NNI --- canopy reflectance sensing --- N mineralization --- farmyard manures --- Triticum aestivum --- discrete wavelet transform --- partial least squares --- hyper-spectra --- rice --- nitrogen management --- reflectance index --- multiple variable linear regression --- Lasso model --- Multiplex®3 sensor --- nitrogen balance index --- nitrogen nutrition index --- nitrogen status diagnosis --- precision nitrogen management --- terrestrial laser scanning --- spectrometer --- plant height --- biomass --- nitrogen concentration --- precision agriculture --- unmanned aerial vehicle (UAV) --- digital camera --- leaf chlorophyll concentration --- portable chlorophyll meter --- crop --- PROSPECT-D --- sensitivity analysis --- UAV multispectral imagery --- spectral vegetation indices --- machine learning --- plant nutrition --- canopy spectrum --- non-destructive nitrogen status diagnosis --- drone --- multispectral camera --- SPAD --- smartphone photography --- fixed-wing UAV remote sensing --- random forest --- canopy reflectance --- crop N status --- Capsicum annuum --- proximal optical sensors --- Dualex sensor --- leaf position --- proximal sensing --- cross-validation --- feature selection --- hyperparameter tuning --- image processing --- image segmentation --- nitrogen fertilizer recommendation --- supervised regression --- RapidSCAN sensor --- nitrogen recommendation algorithm --- in-season nitrogen management --- nitrogen use efficiency --- yield potential --- yield responsiveness --- standard normal variate (SNV) --- continuous wavelet transform (CWT) --- wavelet features optimization --- competitive adaptive reweighted sampling (CARS) --- partial least square (PLS) --- grapevine --- hyperparameter optimization --- multispectral imaging --- precision viticulture --- RGB --- multispectral --- coverage adjusted spectral index --- vegetation coverage --- random frog algorithm --- active canopy sensing --- integrated sensing system --- discrete NIR spectral band data --- soil total nitrogen concentration --- moisture absorption correction index --- particle size correction index --- coupled elimination