scholarly journals Simulation of an Autonomous Mobile Robot for LiDAR-Based In-Field Phenotyping and Navigation

Robotics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 46 ◽  
Author(s):  
Jawad Iqbal ◽  
Rui Xu ◽  
Shangpeng Sun ◽  
Changying Li
Keyword(s):  
Mean Squared Error ◽  
Estimation Error ◽  
Crop Improvement ◽  
Canopy Height ◽  
Agricultural Crop ◽  
Hybrid Strategy ◽  
Agricultural Robots ◽  
Research Fields ◽  
Promising Tool ◽  
Field Phenotyping

The agriculture industry is in need of substantially increasing crop yield to meet growing global demand. Selective breeding programs can accelerate crop improvement but collecting phenotyping data is time- and labor-intensive because of the size of the research fields and the frequency of the work required. Automation could be a promising tool to address this phenotyping bottleneck. This paper presents a Robotic Operating System (ROS)-based mobile field robot that simultaneously navigates through occluded crop rows and performs various phenotyping tasks, such as measuring plant volume and canopy height using a 2D LiDAR in a nodding configuration. The efficacy of the proposed 2D LiDAR configuration for phenotyping is assessed in a high-fidelity simulated agricultural environment in the Gazebo simulator with an ROS-based control framework and compared with standard LiDAR configurations used in agriculture. Using the proposed nodding LiDAR configuration, a strategy for navigation through occluded crop rows is presented. The proposed LiDAR configuration achieved an estimation error of 6.6% and 4% for plot volume and canopy height, respectively, which was comparable to the commonly used LiDAR configurations. The hybrid strategy with GPS waypoint following and LiDAR-based navigation was used to navigate the robot through an agricultural crop field successfully with an root mean squared error of 0.0778 m which was 0.2% of the total traveled distance. The presented robot simulation framework in ROS and optimized LiDAR configuration helped to expedite the development of the agricultural robots, which ultimately will aid in overcoming the phenotyping bottleneck.

scholarly journals Gephebase, a database of genotype–phenotype relationships for natural and domesticated variation in Eukaryotes

2019 ◽  
Vol 48 (D1) ◽  
pp. D696-D703
Author(s):  
Virginie Courtier-Orgogozo ◽  
Laurent Arnoult ◽  
Stéphane R Prigent ◽  
Séverine Wiltgen ◽  
Arnaud Martin
Keyword(s):  
Target Genes ◽  
Crop Improvement ◽  
Carotenoid Content ◽  
Phenotypic Change ◽  
Candidate Gene Approach ◽  
Global Trends ◽  
Research Fields ◽  
Promising Target ◽  
Mutant Phenotypes ◽  
Meta Analyses

Abstract Gephebase is a manually-curated database compiling our accumulated knowledge of the genes and mutations that underlie natural, domesticated and experimental phenotypic variation in all Eukaryotes—mostly animals, plants and yeasts. Gephebase aims to compile studies where the genotype–phenotype association (based on linkage mapping, association mapping or a candidate gene approach) is relatively well supported. Human clinical traits and aberrant mutant phenotypes in laboratory organisms are not included and can be found in other databases (e.g. OMIM, OMIA, Monarch Initiative). Gephebase contains more than 1700 entries. Each entry corresponds to an allelic difference at a given gene and its associated phenotypic change(s) between two species or two individuals of the same species, and is enriched with molecular details, taxonomic information, and bibliographic information. Users can easily browse entries and perform searches at various levels using boolean operators (e.g. transposable elements, snakes, carotenoid content, Doebley). Data is exportable in spreadsheet format. This database allows to perform meta-analyses to extract global trends about the living world and the research fields. Gephebase should also help breeders, conservationists and others to identify promising target genes for crop improvement, parasite/pest control, bioconservation and genetic diagnostic. It is freely available at www.gephebase.org.

scholarly journals Development of second and third-trimester population-specific machine learning pregnancy dating model (Garbhini-GA2) derived from the GARBH-Ini cohort in north India

2021 ◽  
Author(s):  
Nikhita Damaraju ◽  
Ashley Xavier ◽  
Ramya Vijayram ◽  
Bapu Koundinya Desiraju ◽  
Sumit Misra ◽  
...  
Keyword(s):  
Antenatal Care ◽  
Mean Squared Error ◽  
Estimation Error ◽  
Population Data ◽  
First Trimester ◽  
Specific Model ◽  
North India ◽  
Accurate Estimation ◽  
Third Trimester ◽  
Middle Income

Background: The prevalence of preterm birth (PTB) is high in lower and middle-income countries (LMIC) such as India. In LMIC, since a large proportion seeks antenatal care for the first time beyond 14-weeks of pregnancy, accurate estimation of gestational age (GA) using measures derived from ultrasonography scans in the second and third trimesters is of paramount importance. Different models have been developed globally to estimate GA, and currently, LMIC uses Hadlock's formula derived from data based on a North American cohort. This study aimed to develop a population-specific model using data from GARBH-Ini, a multidimensional and ongoing pregnancy cohort established in a district hospital in North India for studying PTB. Methods: Data obtained by longitudinal ultrasonography across all trimesters of pregnancy was used to develop and validate GA models for second and third trimesters. The first trimester GA estimated by ultrasonography was considered the Gold Standard. The second and third trimester GA model named, Garbhini-GA2 is a multivariate random forest model using five ultrasonographic parameters routinely measured during this period. Garbhini-GA2 model was compared to Hadlock and INTERGROWTH-21st models in the TEST set by estimating root mean-squared error, bias and PTB rate. Findings: Garbhini-GA2 reduced the GA estimation error by 23-45% compared to the published models. Furthermore, the PTB rate estimated using Garbhini-GA2 was more accurate when compared to published formulae that overestimated the rate by 1.5-2.0 times. Interpretation: The Garbhini-GA2 model developed is the first of its kind developed solely using Indian population data. The higher accuracy of GA estimation by Garbhini-GA2 emphasises the need to apply population-specific GA formulae to improve antenatal care and better PTB rate estimates.

Amelioration Technology for Agricultural Efficiency

2019 ◽  
pp. 13-31
Author(s):  
Kanchan P. Rathoure
Keyword(s):  
Crop Production ◽  
Phosphate Rock ◽  
Crop Improvement ◽  
The Other ◽  
Agricultural Crop ◽  
Agricultural Efficiency ◽  
Livestock Breeding ◽  
The One ◽  
Rock Minerals ◽  
Growing Population

The sustainable concepts for increased crop production are immediately needed to lower pressure on soils in order to reduce or prevent the negative environmental impacts of rigorous agriculture. One efficient way to increase organic matter in soil is amelioration in soil like compost, biochar, fly ash, red mud, phosphate rock, and other rock minerals. On the one hand, growth of livestock breeding and intensification of crop production has occurred while an increasing shortage of resources can be recognized. On the other hand, urbanization and growing population interconnected with an increased amount of waste output is responsible for environmental hazards and pollution. Therefore, soil amelioration became an efficient means of agricultural crop improvement.

scholarly journals Seeds of Success: Collateral Benefits to Agricultural Crop Improvement, Research, and Education

Crop Science ◽  
2019 ◽  
Vol 59 (6) ◽  
pp. 2429-2442 ◽  
Author(s):  
Stephanie L. Greene ◽  
Daniel Carver ◽  
Colin K. Khoury ◽  
Brian M. Irish ◽  
Peggy Olwell ◽  
...  
Keyword(s):  
Crop Improvement ◽  
Agricultural Crop ◽  
Research And Education

Applying remote sensing expertise to crop improvement: progress and challenges to scale up high throughput field phenotyping from research to industry

2016 ◽  
Author(s):  
David Gouache ◽  
Katia Beauchêne ◽  
Agathe Mini ◽  
Antoine Fournier ◽  
Benoit de Solan ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Throughput ◽  
Crop Improvement ◽  
Scale Up ◽  
Field Phenotyping

Simulated annealing wavelet estimation via fourth‐order cumulant matching

Geophysics ◽  
1996 ◽  
Vol 61 (6) ◽  
pp. 1939-1948 ◽  
Author(s):  
Danilo R. Velis ◽  
Tadeusz J. Ulrych
Keyword(s):  
Simulated Annealing ◽  
Fourth Order ◽  
Simulated Annealing Algorithm ◽  
Numerical Solutions ◽  
Mean Squared Error ◽  
Real Data ◽  
Hybrid Strategy ◽  
Minimum Mean Squared Error ◽  
Highly Nonlinear ◽  
Fourth Order Cumulant

The fourth‐order cumulant matching method has been developed recently for estimating a mixed‐phase wavelet from a convolutional process. Matching between the trace cumulant and the wavelet moment is done in a minimum mean‐squared error sense under the assumption of a non‐Gaussian, stationary, and statistically independent reflectivity series. This leads to a highly nonlinear optimization problem, usually solved by techniques that require a certain degree of linearization, and that invariably converge to the minimum closest to the initial model. Alternatively, we propose a hybrid strategy that makes use of a simulated annealing algorithm to provide reliability of the numerical solutions by reducing the risk of being trapped in local minima. Beyond the numerical aspect, the reliability of the derived wavelets depends strongly on the amount of data available. However, by using a multidimensional taper to smooth the trace cumulant, we show that the method can be used even in a trace‐by‐trace implementation, which is very important from the point of view of stationarity and consistency. We demonstrate the viability of the method under several reflectivity models. Finally, we illustrate the hybrid strategy using marine and field real data examples. The consistency of the results is very encouraging because the improved cumulant matching strategy we describe can be effectively used with a limited amount of data.

A Survey on the Applications of Swarm Intelligence to Software Verification

2020 ◽  
pp. 376-398
Author(s):  
Tsutomu Kumazawa ◽  
Munehiro Takimoto ◽  
Yasushi Kambayashi
Keyword(s):  
Software Engineering ◽  
Formal Verification ◽  
Swarm Intelligence ◽  
Software Verification ◽  
Open Problems ◽  
Software Products ◽  
Research Fields ◽  
Promising Tool ◽  
Verification Tools ◽  
Computational Resources

Applying swarm intelligence techniques to software engineering problems has appealed to both researchers and practitioners in the software engineering community. This chapter describes issues and challenges of its application to formal verification, which is one of the core research fields in software engineering. Formal verification, which explores how to effectively verify software products by using mathematical technique, often suffers from two open problems. One is the so-called state explosion problem that verification tools need too many computational resources to make verification feasible. The other problem is that the results of verification have often too much complexity for users to understand. While a number of research projects have addressed these problems in the context of traditional formal verification, recent researches demonstrate that Swarm Intelligence is a promising tool to tackle the problems. This chapter presents how Swarm Intelligence can be applied to formal verification, and surveys the state-of-the-art techniques.

scholarly journals Predicting 15O-Water PET cerebral blood flow maps from multi-contrast MRI using a deep convolutional neural network with evaluation of training cohort bias

2019 ◽  
Vol 40 (11) ◽  
pp. 2240-2253 ◽  
Author(s):  
Jia Guo ◽  
Enhao Gong ◽  
Audrey P Fan ◽  
Maged Goubran ◽  
Mohammad M Khalighi ◽  
...  
Keyword(s):  
Neural Network ◽  
Blood Flow ◽  
Cerebral Blood Flow ◽  
Convolutional Neural Network ◽  
Mean Squared Error ◽  
Estimation Error ◽  
Similarity Index ◽  
Structural Similarity ◽  
Target Population ◽  
Deep Convolutional Neural Network

To improve the quality of MRI-based cerebral blood flow (CBF) measurements, a deep convolutional neural network (dCNN) was trained to combine single- and multi-delay arterial spin labeling (ASL) and structural images to predict gold-standard 15O-water PET CBF images obtained on a simultaneous PET/MRI scanner. The dCNN was trained and tested on 64 scans in 16 healthy controls (HC) and 16 cerebrovascular disease patients (PT) with 4-fold cross-validation. Fidelity to the PET CBF images and the effects of bias due to training on different cohorts were examined. The dCNN significantly improved CBF image quality compared with ASL alone (mean ± standard deviation): structural similarity index (0.854 ± 0.036 vs. 0.743 ± 0.045 [single-delay] and 0.732 ± 0.041 [multi-delay], P <  0.0001); normalized root mean squared error (0.209 ± 0.039 vs. 0.326 ± 0.050 [single-delay] and 0.344 ± 0.055 [multi-delay], P <  0.0001). The dCNN also yielded mean CBF with reduced estimation error in both HC and PT ( P <  0.001), and demonstrated better correlation with PET. The dCNN trained with the mixed HC and PT cohort performed the best. The results also suggested that models should be trained on cases representative of the target population.

scholarly journals MINIMAX FILTERING IN WIRELESS SENSOR AND ACTOR NETWORKS

2013 ◽  
pp. 268-271
Author(s):  
K. RAMESH ◽  
S. Vasundra
Keyword(s):  
Kalman Filtering ◽  
Estimation Error ◽  
Wireless Sensor ◽  
Location Prediction ◽  
Worst Case ◽  
Hybrid Strategy ◽  
Energy Consumptions ◽  
Actor Networks ◽  
Power And Energy ◽  
Location Updating

In this paper to handle the mobility of actors a hybrid strategy that includes location updating and location prediction is used. The usage of Kalman Filtering in location prediction high power and energy consumptions. To avoid the drawbacks of Kalman Filtering in location prediction, we make use of Mini max filtering (also Known as H∞ filtering). Mini max Filter has been used in WSANs by minimizing the estimation error and maximizing the worst case adversary noise. Mini max filtering will also minimize power and energy consumptions.

scholarly journals Molecular advances on agricultural crop improvement to meet current cultivating demands

2019 ◽  
Vol 12 (2) ◽  
pp. 39-60
Author(s):  
T. Margaritopoulou ◽  
D. Milioni
Keyword(s):  
Genomic Selection ◽  
Quantitative Traits ◽  
Seed Quality ◽  
Association Studies ◽  
Crop Improvement ◽  
Genome Wide Association Studies ◽  
Whole Genome ◽  
Agricultural Crop ◽  
Marker Assisted Breeding ◽  
Breeding Programs

Abstract Sunflower, maize and potato are among the world’s principal crops. In order to improve various traits, these crops have been genetically engineered to a great extent. Even though molecular markers for simple traits such as, fertility, herbicide tolerance or specific pathogen resistance have been successfully used in marker-assisted breeding programs for years, agronomical important complex quantitative traits like yield, biotic and abiotic stress resistance and seed quality content are challenging and require whole genome approaches. Collections of genetic resources for these crops are conserved worldwide and represent valuable resources to study complex traits. Nowadays technological advances and the availability of genome sequence have made novel approaches on the whole genome level possible. Molecular breeding, including both transgenic approach and marker-assisted breeding have facilitated the production of large amounts of markers for high density maps and allowed genome-wide association studies and genomic selection in sunflower, maize and potato. Marker-assisted selection related to hybrid performance has shown that genomic selection is a successful approach to address complex quantitative traits and to facilitate speeding up breeding programs in these crops in the future.

Sign in / Sign up

Export Citation Format

Share Document