Assessment of software-derived predictive algorithms for platelet yield and blood cell count after apheresis.

INTRODUCTION: Algorithms have been developed to predict the platelet yield after apheresis from the donor's data, as well as the effect on the blood cell count, to extract an acceptable platelet number without affecting the donor. However, the evaluation of these algorithms has not been widely reported. This study aimed to assess the accuracy of the predictive algorithms of the Trima Accel v. 6 blood collection system. METHODS: Platelet concentrates (PCs) obtained by apheresis were analyzed. Platelet count and hematocrit were compared pre- and post-apheresis. Calculated post-apheresis platelet count (CPAPC), hematocrit (CPAH), and platelet yield (CPY), and their actual values were correlated. The bias of the algorithms was assessed with Bland-Altman plots, and the prediction of the extraction of single or double platelet products was evaluated. RESULTS: Two hundred and seventy-nine PCs were analyzed. Post-apheresis platelet count (PAPC) and hematocrit were decreased. A moderate correlation was observed between CPY and the actual yield, with a negative bias, and a trend to increase alongside the magnitude of the measurements. CPAPC and CPAH were strongly correlated with their actual values without bias. Prediction of single or double platelet product extraction showed a significant agreement with the actual outcomes. CONCLUSIONS: The predictive algorithm for the platelet yield showed bias, and a trend to underestimate the actual platelet yields when they are higher. The algorithms for the prediction of the PAPC and hematocrit did not show bias, proving their accuracy. Prediction of a single or double platelet product extraction has a strong agreement with the APY.

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz).

BACKGROUND: Rapid non-destructive measurements to predict cassava root yield over the full growing season through large numbers of germplasm and multiple environments is a huge challenge in Cassava breeding programs. As opposed to waiting until the harvest season, multispectral imagery using unmanned aerial vehicles (UAV) are capable of measuring the canopy metrics and vegetation indices (VIs) traits at different time points of the growth cycle. This resourceful time series aerial image processing with appropriate analytical framework is very important for the automatic extraction of phenotypic features from the image data. Many studies have demonstrated the usefulness of advanced remote sensing technologies coupled with machine learning (ML) approaches for accurate prediction of valuable crop traits. Until now, Cassava has received little to no attention in aerial image-based phenotyping and ML model testing. RESULTS: To accelerate image processing, an automated image-analysis framework called CIAT Pheno-i was developed to extract plot level vegetation indices/canopy metrics. Multiple linear regression models were constructed at different key growth stages of cassava, using ground-truth data and vegetation indices obtained from a multispectral sensor. Henceforth, the spectral indices/features were combined to develop models and predict cassava root yield using different Machine learning techniques. Our results showed that (1) Developed CIAT pheno-i image analysis framework was found to be easier and more rapid than manual methods. (2) The correlation analysis of four phenological stages of cassava revealed that elongation (EL) and late bulking (LBK) were the most useful stages to estimate above-ground biomass (AGB), below-ground biomass (BGB) and canopy height (CH). (3) The multi-temporal analysis revealed that cumulative image feature information of EL + early bulky (EBK) stages showed a higher significant correlation (r = 0.77) for Green Normalized Difference Vegetation indices (GNDVI) with BGB than individual time points. Canopy height measured on the ground correlated well with UAV (CHuav)-based measurements (r = 0.92) at late bulking (LBK) stage. Among different image features, normalized difference red edge index (NDRE) data were found to be consistently highly correlated (r = 0.65 to 0.84) with AGB at LBK stage. (4) Among the four ML algorithms used in this study, k-Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machine (SVM) showed the best performance for root yield prediction with the highest accuracy of R2 = 0.67, 0.66 and 0.64, respectively. CONCLUSION: UAV platforms, time series image acquisition, automated image analytical framework (CIAT Pheno-i), and key vegetation indices (VIs) to estimate phenotyping traits and root yield described in this work have great potential for use as a selection tool in the modern cassava breeding programs around the world to accelerate germplasm and varietal selection. The image analysis software (CIAT Pheno-i) developed from this study can be widely applicable to any other crop to extract phenotypic information rapidly.

INDISIM-Denitrification, an individual-based model for study the denitrification process.

Denitrification is one of the key processes of the global nitrogen (N) cycle driven by bacteria. It has been widely known for more than 100 years as a process by which the biogeochemical N-cycle is balanced. To study this process, we develop an individual-based model called INDISIM-Denitrification. The model embeds a thermodynamic model for bacterial yield prediction inside the individual-based model INDISIM and is designed to simulate in aerobic and anaerobic conditions the cell growth kinetics of denitrifying bacteria. INDISIM-Denitrification simulates a bioreactor that contains a culture medium with succinate as a carbon source, ammonium as nitrogen source and various electron acceptors. To implement INDISIM-Denitrification, the individual-based model INDISIM was used to give sub-models for nutrient uptake, stirring and reproduction cycle. Using a thermodynamic approach, the denitrification pathway, cellular maintenance and individual mass degradation were modeled using microbial metabolic reactions. These equations are the basis of the sub-models for metabolic maintenance, individual mass synthesis and reducing internal cytotoxic products. The model was implemented in the open-access platform NetLogo. INDISIM-Denitrification is validated using a set of experimental data of two denitrifying bacteria in two different experimental conditions. This provides an interactive tool to study the denitrification process carried out by any denitrifying bacterium since INDISIM-Denitrification allows changes in the microbial empirical formula and in the energy-transfer-efficiency used to represent the metabolic pathways involved in the denitrification process. The simulator can be obtained from the authors on request.

A smartphone-based apple yield estimation application using imaging features and the ANN method in mature period

Apple yield estimation using a smartphone with image processing technology offers advantages such as low cost, quick access and simple operation. This article proposes distribution framework consisting of the acquisition of fruit tree images, yield prediction in smarphone client, data processing and model calculation in server client for estimating the potential fruit yield. An image processing method was designed including the core steps of image segmentation with R/B value combined with V value and circle-fitting using curvature analysis. This method enabled four parameters to be obtained, namely, total identified pixel area (TP), fitting circle amount (FC), average radius of the fitting circle (RC) and small polygon pixel area (SP). A individual tree yield estimation model on an ANN (Artificial Neural Network) was developed with three layers, four input parameters, 14 hidden neurons, and one output parameter. The system was used on an experimental Fuji apple (Malus domestica Borkh. cv. Red Fuji) orchard. Twenty-six tree samples were selected from a total of 80 trees according to the multiples of the number three for the establishment model, whereby 21 groups of data were trained and 5 groups o data were validated. The R2 value for the training datasets was 0.996 and the relative root mean squared error (RRMSE) value 0.063. The RRMSE value for the validation dataset was 0.284 Furthermore, a yield map with 80 apple trees was generated, and the space distribution o the yield was identified. It provided appreciable decision support for site-specific management.(AU)

A smartphone-based apple yield estimation application using imaging features and the ANN method in mature period

ABSTRACT: Apple yield estimation using a smartphone with image processing technology offers advantages such as low cost, quick access and simple operation. This article proposes distribution framework consisting of the acquisition of fruit tree images, yield prediction in smarphone client, data processing and model calculation in server client for estimating the potential fruit yield. An image processing method was designed including the core steps of image segmentation with R/B value combined with V value and circle-fitting using curvature analysis. This method enabled four parameters to be obtained, namely, total identified pixel area (TP), fitting circle amount (FC), average radius of the fitting circle (RC) and small polygon pixel area (SP). A individual tree yield estimation model on an ANN (Artificial Neural Network) was developed with three layers, four input parameters, 14 hidden neurons, and one output parameter. The system was used on an experimental Fuji apple (Malus domestica Borkh. cv. Red Fuji) orchard. Twenty-six tree samples were selected from a total of 80 trees according to the multiples of the number three for the establishment model, whereby 21 groups of data were trained and 5 groups o data were validated. The R2 value for the training datasets was 0.996 and the relative root mean squared error (RRMSE) value 0.063. The RRMSE value for the validation dataset was 0.284 Furthermore, a yield map with 80 apple trees was generated, and the space distribution o the yield was identified. It provided appreciable decision support for site-specific management.

A smartphone-based apple yield estimation application using imaging features and the ANN method in mature period

ABSTRACT: Apple yield estimation using a smartphone with image processing technology offers advantages such as low cost, quick access and simple operation. This article proposes distribution framework consisting of the acquisition of fruit tree images, yield prediction in smarphone client, data processing and model calculation in server client for estimating the potential fruit yield. An image processing method was designed including the core steps of image segmentation with R/B value combined with V value and circle-fitting using curvature analysis. This method enabled four parameters to be obtained, namely, total identified pixel area (TP), fitting circle amount (FC), average radius of the fitting circle (RC) and small polygon pixel area (SP). A individual tree yield estimation model on an ANN (Artificial Neural Network) was developed with three layers, four input parameters, 14 hidden neurons, and one output parameter. The system was used on an experimental Fuji apple (Malus domestica Borkh. cv. Red Fuji) orchard. Twenty-six tree samples were selected from a total of 80 trees according to the multiples of the number three for the establishment model, whereby 21 groups of data were trained and 5 groups o data were validated. The R2 value for the training datasets was 0.996 and the relative root mean squared error (RRMSE) value 0.063. The RRMSE value for the validation dataset was 0.284 Furthermore, a yield map with 80 apple trees was generated, and the space distribution o the yield was identified. It provided appreciable decision support for site-specific management.

Genetic control of soybean (Glycine max) yield in the absence and presence of the Asian rust fungus (Phakopsora pachyrhizi)

Soybean is one of the most important crops in Brazil and continuously generates demands for production technologies, such as cultivars resistant to diseases. In recent years, the Asian rust fungus (Phakopsora pachyrhizi Syd. & P. Syd 1914) has caused severe yield losses and the development of resistant cultivars is the best means of control. Understanding the genetic control and estimating parameters associated with soybean (Glycine max) resistance to P. pachyrhizi will provide essential information for cultivar selection. We investigated quantitative genetic control of P. pachyrhizi and estimated parameters associated to soybean yield in the absence and presence of this phytopathogen. Six cultivars and their 15 diallel derived F2 and F3 generations were assessed in experiments carried out in the absence and presence of P. pachyrhizi. The results indicated that soybean yield in the presence and absence of P. pachyrhizi is controlled by polygenes expressing predominantly additive effects that can be selected to develop new cultivars resistant or tolerant to P. pachyrhizi. These cultivars may prove to be a useful and more durable alternative than cultivars carrying major resistance genes.