coveR: An R package for processing Digital Cover Photography images to retrieve forest canopy attributes

Digital Cover Photography (DCP) is an increasingly popular tool for estimating canopy cover and leaf area index (LAI). However, existing solutions to process canopy images are predominantly tailored for fisheye photography, whereas open-access tools for DCP are lacking. We developed an R package (coveR) to support the whole processing of DCP images in an automated, fast and reproducible way. The package functions, which are designed for step-by-step single-image analysis, can be performed sequentially in a pipeline and also allow simple implementation of batch-processing bunches of images. A case study is presented to demonstrate the reliability of canopy attributes derived from coveR in pure beech (Fagus sylvatica L.) stands with variable canopy density and structure. Estimates of gap fraction and effective LAI from DCP were validated against reference measurements obtained from terrestrial laser scanning. By providing a simple, transparent and flexible image processing procedure, coveR supported the use of DCP for routine measurements and monitoring of forest canopy attributes. This, combined with the implementability of DCP in many devices, including smartphones, micro-cameras, and remote trail cameras, can greatly expand the accessibility of the method also to non-experts.

MODEL PREDICTIVE CONTROL OF AN AUV USING DE-COUPLED APPROACH

This paper considers the decoupled dynamics and control of an Autonomous Underwater Vehicle (AUV). The decoupled model consists of speed, steering and depth subsystems. Generally AUV model is unstable and nonlinear. The central theme of this paper is the development of model predictive control (MPC) for underwater robotic vehicle for ocean survey applications. The proposed MPC for decoupled structure can have simple implementation. Simulation results have been presented which confirm satisfactory performance. Decoupled approach is well suitable for applying control.

An Improved DCP-Based Image Defogging Algorithm Combined with Adaptive Fusion Strategy

Dark channel prior (DCP) has been widely used in single image defogging because of its simple implementation and satisfactory performance. This paper addresses the shortcomings of the DCP-based defogging algorithm and proposes an optimized method by using an adaptive fusion mechanism. This proposed method makes full use of the smoothing and “squeezing” characteristics of the Logistic Function to obtain more reasonable dark channels avoiding further refining the transmission map. In addition, a maximum filtering on dark channels is taken to improve the accuracy of dark channels around the object boundaries and the overall brightness of the defogged clear images. Meanwhile, the location information and brightness information of fog image are weighed to obtain more accurate atmosphere light. Quantitative and qualitative comparisons show that the proposed method outperforms state-of-the-art image defogging algorithms.

Power Sharing Control in a Grid-Tied DC Microgrid: Controller Hardware in the Loop Validation

This article presents the development of a low-cost control hardware in the loop platform for the validation and analysis of controllers used for the management of power sharing between the main grid and a DC microgrid. The platform is made up of two parts: a main grid interconnection system emulator (MGISE) and a controller under test (CUT). The MGISE operates on a 260 V DC bus and includes a 1000 W photovoltaic array, a DC variable load and a single H full bridge converter (HFBC). The CUT includes a phase locked loop and a main cascade control structure composed of two PI controllers. Both the MGISE and the CUT were embedded on an NI myRIO-1900 development board and programmed using LabVIEW virtual instrumentation software. These devices communicate with each other using analog signals representing the AC side current, the DC side voltage, and the HFBC control signal. The MGISE operates with an integration time of 6 µs and its performance is validated by comparing it with a simulation in PSIM. The integration time of the MGISE, the development boards used, as well as its programming environment, and the results obtained from the comparison with PSIM simulation, show that the proposed platform is useful for the validation of controllers for power sharing, with a simple implementation process compared to other hardware description methods and with a low-cost platform.

A combined method of formation of a cryptographic key with secret modification of the results of synchronization of artificial neural networks

This article discusses one of the ways to generate a common cryptographic key using synchronized artificial neural networks. This option is based on a combined method of forming a cryptographic key [1]. The proposed combined formation consists of two stages: the formation of partially coinciding binary sequences using synchronized artificial neural networks and the elimination of mismatched bits by open comparison of the parities of bit pairs. The purpose of this article is to increase the cryptographic strength of this method in relation to a cryptanalyst. In this regard, it is proposed to prematurely interrupt the synchronization process at the first stage of the combined method and make changes to the resulting binary sequence by randomly inverting a certain number of bits. To confirm the quality of this method, possible attacks are considered and the scale of enumeration of possible values is illustrated. The results obtained showed that the combined method of forming a cryptographic key with a secret modification of the synchronization results of artificial neural networks, proposed in this article, provides its high cryptographic strength, commensurate with the cryptographic strength of modern symmetric encryption algorithms, with a relatively simple implementation.

MiSiC, a general deep learning-based method for the high-throughput cell segmentation of complex bacterial communities

Studies of bacterial communities, biofilms and microbiomes, are multiplying due to their impact on health and ecology. Live imaging of microbial communities requires new tools for the robust identification of bacterial cells in dense and often inter-species populations, sometimes over very large scales. Here, we developed MiSiC, a general deep-learning-based 2D segmentation method that automatically segments single bacteria in complex images of interacting bacterial communities with very little parameter adjustment, independent of the microscopy settings and imaging modality. Using a bacterial predator-prey interaction model, we demonstrate that MiSiC enables the analysis of interspecies interactions, resolving processes at subcellular scales and discriminating between species in millimeter size datasets. The simple implementation of MiSiC and the relatively low need in computing power make its use broadly accessible to fields interested in bacterial interactions and cell biology.

Computational Prediction of Compound–Protein Interactions for Orphan Targets Using CGBVS

A variety of Artificial Intelligence (AI)-based (Machine Learning) techniques have been developed with regard to in silico prediction of Compound–Protein interactions (CPI)—one of which is a technique we refer to as chemical genomics-based virtual screening (CGBVS). Prediction calculations done via pairwise kernel-based support vector machine (SVM) is the main feature of CGBVS which gives high prediction accuracy, with simple implementation and easy handling. We studied whether the CGBVS technique can identify ligands for targets without ligand information (orphan targets) using data from G protein-coupled receptor (GPCR) families. As the validation method, we tested whether the ligand prediction was correct for a virtual orphan GPCR in which all ligand information for one selected target was omitted from the training data. We have specifically expressed the results of this study as applicability index and developed a method to determine whether CGBVS can be used to predict GPCR ligands. Validation results showed that the prediction accuracy of each GPCR differed greatly, but models using Multiple Sequence Alignment (MSA) as the protein descriptor performed well in terms of overall prediction accuracy. We also discovered that the effect of the type compound descriptors on the prediction accuracy was less significant than that of the type of protein descriptors used. Furthermore, we found that the accuracy of the ligand prediction depends on the amount of ligand information with regard to GPCRs related to the target. Additionally, the prediction accuracy tends to be high if a large amount of ligand information for related proteins is used in the training.