scholarly journals Stored Grain Pack Factor Measurements for Soybeans, Grain Sorghum, Oats, Barley, and Wheat

2018 ◽  
Vol 61 (2) ◽  
pp. 747-757
Author(s):  
Rumela Bhadra ◽  
Mark E. Casada ◽  
Aaron P. Turner ◽  
Michael D. Montross ◽  
Sidney A. Thompson ◽  
...  
Keyword(s):  
Initial Density ◽  
Field Measurements ◽  
Grain Sorghum ◽  
Barley Grain ◽  
Average Error ◽  
Prediction Errors ◽  
Service Agency ◽  
Stored Grain ◽  
Volume Measurements ◽  
Farm Service Agency

Abstract. Grain and oilseed crops stored in bins undergo compaction due to overbearing pressure of the grain inside the structure. Thus, volume measurements of grain in bins need to be combined with the amount of packing (usually called pack factor) in addition to the initial density so that the mass in the structure can be calculated. Multiple pack factor prediction methods are in use in the grain industry, but they have only been validated in the literature and compared with field data for corn and hard red winter wheat. Predictions from WPACKING, the program in ASABE Standard EP413.2, and two standard USDA methods, the USDA Risk Management Agency (RMA) and USDA Farm Service Agency-Warehouse Licensing and Examination Division (FSA-W) methods, were compared to field measurements of 92 bins containing soybeans, grain sorghum, oats, barley, or soft white or durum wheat. The WPACKING predictions had the lowest absolute average error of predicted mass for soybeans, grain sorghum, barley, and wheat, while the FSA-W method had the lowest error for oats. The RMA method gave the largest prediction errors for all five crops and struggled especially with the low-density, high-compaction crops oats and barley, giving average percent absolute errors near or above 10% in both cases. Overall, WPACKING, the RMA method, and the FSA-W method had average percent absolute errors of 2.09%, 5.65%, and 3.62%, respectively, for the 92 bins. These results can be used to improve pack factor predictions for the grain industry. Keywords: Barley, Grain, Grain sorghum, Oats, Pack factor, Sorghum, Soybeans, Steel and concrete bins, Stored grain inventory, Test weight, Wheat.

scholarly journals Non-Destructive Fuel Volume Measurements Can Estimate Fine-Scale Biomass across Surface Fuel Types in a Frequently Burned Ecosystem

Fire ◽  
2021 ◽  
Vol 4 (3) ◽  
pp. 36
Author(s):  
Quinn A. Hiers ◽  
E. Louise Loudermilk ◽  
Christie M. Hawley ◽  
J. Kevin Hiers ◽  
Scott Pokswinski ◽  
...  
Keyword(s):  
Bulk Density ◽  
Pinus Palustris ◽  
Field Measurements ◽  
Complex Surface ◽  
Fuel Type ◽  
Field Methods ◽  
Volume Measurements ◽  
Woody Litter ◽  
Non Destructive ◽  
Surface Vegetation

Measuring wildland fuels is at the core of fire science, but many established field methods are not useful for ecosystems characterized by complex surface vegetation. A recently developed sub-meter 3D method applied to southeastern U.S. longleaf pine (Pinus palustris) communities captures critical heterogeneity, but similar to any destructive sampling measurement, it relies on separate plots for calculating loading and consumption. In this study, we investigated how bulk density differed by 10-cm height increments among three dominant fuel types, tested predictions of consumption based on fuel type, height, and volume, and compared this with other field measurements. The bulk density changed with height for the herbaceous and woody litter fuels (p < 0.001), but live woody litter was consistent across heights (p > 0.05). Our models predicted mass well based on volume and height for herbaceous (RSE = 0.00911) and woody litter (RSE = 0.0123), while only volume was used for live woody (R2 = 0.44). These were used to estimate consumption based on our volume-mass predictions, linked pre- and post-fire plots by fuel type, and showed similar results for herbaceous and woody litter when compared to paired plots. This study illustrates an important non-destructive alternative to calculating mass and estimating fuel consumption across vertical volume distributions at fine scales.

A comparison among approaches for recommending learning objects through collaborative filtering algorithms

2017 ◽  
Vol 51 (1) ◽  
pp. 35-51
Author(s):  
Henrique Lemos dos Santos ◽  
Cristian Cechinel ◽  
Ricardo Matsumura Araújo
Keyword(s):  
Collaborative Filtering ◽  
Learning Objects ◽  
Learning Goals ◽  
Average Error ◽  
Neighborhood Size ◽  
Relevant Parameter ◽  
Prediction Errors ◽  
Content Type ◽  
User Coverage ◽  
The Impact

Purpose The purpose of this paper is to present the results of a comparison among three different approaches for recommending learning objects (LO) inside a repository. The comparison focuses not only on prediction errors but also on the coverage of each tested configuration. Design/methodology/approach The authors compared the offline evaluation by using pure collaborative filtering (CF) algorithms with two other different combinations of pre-processed data. The first approach for pre-processing data consisted of clustering users according to their disciplines resemblance, while the second approach consisted of clustering LO according to their textual similarity regarding title and description. The three methods were compared with respect to the mean average error between predicted values and real values. Moreover, we evaluated the impact of the number of clusters and neighborhood size on the user-coverage. Findings Clustering LO has improved the prediction error measure with a small loss on user-coverage when compared to the pure CF approach. On the other hand, the approach of clustering users failed in both the error and in user-space coverage. It also became clear that the neighborhood size is the most relevant parameter to determine how large the coverage will be. Research limitations The methods proposed here were not yet evaluated in a real-world scenario, with real users opinions about the recommendations and their respective learning goals. Future work is still required to evaluate users opinions. Originality/value This research provides evidence toward new recommendation methods directed toward LO repositories.

scholarly journals Developing and Implementing Farm Stress Training to Address Agricultural Producer Mental Health

2020 ◽  
pp. 152483992093184
Author(s):  
Courtney Cuthbertson ◽  
Alison Brennan ◽  
John Shutske ◽  
Lori Zierl ◽  
Andrea Bjornestad ◽  
...  
Keyword(s):  
Mental Health ◽  
Health Resources ◽  
Service Agency ◽  
Department Of Agriculture ◽  
Agricultural Producers ◽  
Knowledge And Skills ◽  
Resources Evaluation ◽  
Agricultural Producer ◽  
Farm Service Agency ◽  
Practice Skills

Farmers and ranchers (agricultural producers) have higher psychological distress and suicide rates than the general population. Poorer mental health status and outcomes among producers are often attributed to the continuously challenging economic, social, and climate-related changes to agriculture as an occupation and industry. This article describes the development of a training program for agribusiness professionals from the U.S. Department of Agriculture Farm Service Agency (N = 500) who work with producers, as they regularly interact with producers and thus are in a position to readily offer helpful mental health resources. The goal of the program was for agribusiness professionals to build skills and confidence to identify and respond to distressed producers. The educational program was offered primarily online and included a 1-day in-person training to practice skills to communicate with distressed producers and refer them to appropriate mental health resources. Evaluation of the program demonstrated participants experienced gains in knowledge and skills related to identifying and helping distressed producers.

Do farm service agency borrowers' double minority labels lead to more unfavorable loan packaging terms?

2020 ◽  
Vol 80 (5) ◽  
pp. 633-646
Author(s):  
Jyotsna Ghimire ◽  
Cesar L. Escalante ◽  
Ramesh Ghimire ◽  
Charles B. Dodson
Keyword(s):  
Interest Rate ◽  
Interest Rates ◽  
Simulation Optimization ◽  
Service Agency ◽  
Institutional Reforms ◽  
Content Type ◽  
Loan Terms ◽  
And Gender ◽  
Farm Service Agency ◽  
Double Minority

PurposeThis study adds a new dimension in the study of racial and gender bias in farm lending. Most previous studies analyzed the separate effects of race and gender attributes on loan approval decisions. The analysis focuses on the stipulation of loan terms (loan amount, interest rate and maturity) among approved farm loan applications. The time period analyzed spans from 2004 until 2014 during which the government has undertaken reforms to improve delivery of loan services to its clientele of minority farmers. Thus, this study's findings could help validate the effectivity of such institutional reforms affecting Farm Service Agency (FSA) lending operations.Design/methodology/approachThis study utilizes a national direct loan origination data from the FSA of the U.S. Department of Agriculture (USDA) collected from 2004 to 2014. The analysis begins by identifying significant differences in cross-tabulations of loan terms among different racial and gender classes. Seemingly unrelated regression (SUR) regression techniques are then applied for a system of equations involving the three loan packaging components. The combined effects of the prescribed loan packaging terms are subsequently analyzed under a simulation-optimization framework.FindingsRegression results validate that indeed, relative to White American borrowers, certain minority borrowers are accommodated with lower loan amounts at higher interest rates and with shorter maturities. However, these decisions seem to be prompted by credit risk management considerations. The most compelling findings include the insignificance of all double minority labeling variables, except for the interest rate equation that even produced favorable results for Hispanic American females. Simulation-optimization results further reinforce that even when one or two unfavorable loan terms are included in the packaging, double minority borrowers end up with better profitability and liquidity positions.Practical implicationsThis study provides a different perspective in dealing with the controversial minority bias in lending by presenting evidence gathered from a government farm lending institution. The USDA-FSA has been sued in numerous occasions by minority borrowers. Since then, however, it has deliberately implemented institutional reforms to rectify previous errors. This study provides empirical evidence strengthening FSA's claim of its intention to improve its delivery of loan services, especially for its socially disadvantaged borrowers with double minority classification.Originality/valueThis study pioneers the analysis of the double minority labeling effect on farm lending decisions. Its contributions to literature are further enhanced by its goal to validate the effectiveness of FSA institutional reforms undertaken since the early 2000s in order to improve credit access of and delivery of credit services to minority farm borrowers, especially those that belong to more than one minority classification.

FSA farm loan repayment under economic recession and drought conditions

2016 ◽  
Vol 76 (4) ◽  
pp. 445-461 ◽  
Author(s):  
Cesar Escalante ◽  
Minrong Song ◽  
Charles Dodson
Keyword(s):  
Commodity Prices ◽  
Economic Recession ◽  
Analytical Framework ◽  
Duration Model ◽  
Service Agency ◽  
Data Set ◽  
Content Type ◽  
Drought Conditions ◽  
Business Structures ◽  
Farm Service Agency

Purpose The purpose of this paper is to analyze the repayment records of Farm Service Agency (FSA) borrowers in two distinct US farming regions that have been experienced serious drought conditions even as the US economy was going through a recession. The analysis will identify factors that significantly influence both the probability of FSA borrowers’ survival (capability to remain in good credit standing) and temporal endurance (or length of period of good standing with creditor). Design/methodology/approach This analysis utilizes a data set of farm borrowers of the Farm Service Agency that regular farm lenders have classified as “marginal” relative to other borrowers. The research goal is addressed by confining this study’s regional focus to the Southeast and Midwest that have both dealt with financial stress arising from abnormal natural and economic conditions prevailing during the same time period. A split population duration model is employed to separately identify determinants of the probability and duration of survival (condition of good credit standing). Findings This study’s results indicate that larger loan balances, declining commodity prices, and the severity of drought conditions have adversely affected both the borrowing farms’ probability of survival and temporal endurance in terms of maintaining non-delinquent borrower standing. Notably, Midwestern farms have been relatively less affected by drought conditions compared to Southeastern farms. This study’s results validate the contention that the farms’ capability to survive and the duration of their survival can be attributed to differences in regional resource endowments, farming activities, and business structures. Originality/value This study’s analytical framework departs from the basic duration model approach by considering temporal endurance, in addition to survival probability analysis. This study’s original contributions are enhanced by its specific focus on the contrasting farm business structures and operating environments in the Midwest and Southeast regions.

scholarly journals Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6022
Author(s):  
Fabian Schrumpf ◽  
Patrick Frenzel ◽  
Christoph Aust ◽  
Georg Osterhoff ◽  
Mirco Fuchs
Keyword(s):  
Blood Pressure ◽  
Prediction Error ◽  
Machine Learning Techniques ◽  
Systematic Evaluation ◽  
Average Error ◽  
Prediction Errors ◽  
Invasive Blood Pressure ◽  
Specific Data ◽  
Non Invasive ◽  
Learning Techniques

Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we use this parameterization to train NNs with a larger PPG dataset and carry out a systematic evaluation of the predicted blood pressure. The analysis revealed a strong systematic increase of the prediction error towards less frequent BP values across NN architectures. Moreover, we tested different train/test set split configurations which underpin the importance of a careful subject-aware dataset assignment to prevent overly optimistic results. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply different personalization techniques and retrain our NNs with subject-specific data for both the PPG-only and rPPG case. Whilst the particular technique is less important, personalization reduces the prediction errors significantly.

scholarly journals Forecasting algorithm of tourism service trade based on PSO-optimized hybrid RVM model

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Xiaoying Dong ◽  
Xuanjun Chen
Keyword(s):  
Search Algorithm ◽  
Principal Component ◽  
Average Error ◽  
Prediction Errors ◽  
Service Trade ◽  
Total Import ◽  
Forecast Result ◽  
Import And Export ◽  
Tourism Service ◽  
The Impact

AbstractAs a comprehensive form of trade, tourism service trade has had a profound impact on the economies of various countries. This research mainly discusses the tourism service trade forecasting algorithm based on the PSO-optimized hybrid RVM model. This study extracts 8 indicators including gross national product, total fixed asset investment, total import and export, China's import and export tariff rate, the exchange rate of renminbi to the US dollar, and the global economic growth rate. The same as the impact indicators of tourism service trade, but there is a certain degree of redundancy and correlation in these indicators. In order to measure the correlation between the evaluation indicators, the autocorrelation evaluation function in MATLAB is used, and the principal component analysis method is used to extract the principal components that can represent the indicators in a larger percentage. In order to improve the prediction accuracy of the RVM model, based on the adaptive construction model structure and initial model weights, the PSO algorithm is used to optimize the RVM model weights. The optimization process takes the minimum error of the RVM model as the algorithm search target, and each represents the RVM model. The algorithm finds the value and threshold of the optimal RVM model through the particle swarm tracking search algorithm and then uses the original RVM model and the optimized RVM prediction respectively total amount of tourism service trade in City A, and compares the prediction errors of the single RVM method and the PSO-optimized RVM method, and analyzes the degree of model prediction error reduction after the PSO model optimizes the RVM model. According to the forecast result, the relative average error of 2020 is 5.7%, and the forecast result is relatively accurate. This research is helpful to provide scientific reference for my country's tourism service trade.

scholarly journals Simulation of Batch Slow Pyrolysis of Biomass Materials Using the Process-Flow-Diagram COCO Simulator

Processes ◽  
2019 ◽  
Vol 7 (11) ◽  
pp. 775 ◽  
Author(s):  
Chaiyot Tangsathitkulchai ◽  
Natthaya Punsuwan ◽  
Piyarat Weerachanchai
Keyword(s):  
Simulation Method ◽  
Simulation Program ◽  
Flow Diagram ◽  
Average Error ◽  
Prediction Errors ◽  
Thermodynamic Consideration ◽  
Slow Pyrolysis ◽  
Product Yields ◽  
Gas Products ◽  
Solid Liquid

The commercial COCO simulation program was used to mimic the experimental slow pyrolysis process of five different biomasses based on thermodynamic consideration. The program generated the optimum set of reaction kinetic parameters and reaction stoichiometric numbers that best described the experimental yields of solid, liquid and gas products. It was found that the simulation scheme could predict the product yields over the temperature range from 300 to 800 °C with reasonable accuracy of less than 10% average error. An attempt was made to generalize the biomass pyrolysis behavior by dividing the five biomasses into two groups based on the single-peak and two-peak characteristics of the DTG (derivative thermogravimetry) curves. It was found that this approximate approach was able to predict the product yields reasonably well. The proposed simulation method was extended to the analysis of slow pyrolysis results derived from previous investigations. The results obtained showed that the prediction errors of product yields were relatively large, being 12.3%, 10.6%, and 27.5% for the solid, liquid, and gas products, respectively, possibly caused by differing pyrolysis conditions from those used in the simulation. The prediction of gas product compositions by the simulation program was reasonably satisfactory, but was less accurate for predicting the compositions of liquid products analyzed in forms of hydrocarbons, aromatics and oxygenated fractions. In addition, information on the kinetics of thermal decomposition of biomass in terms of the variation of fractional conversion with time was also derived as a function of temperature and biomass type.

Prediction of adult height by machine learning technique

2021 ◽  
Author(s):  
Michael Shmoish ◽  
Alina German ◽  
Nurit Devir ◽  
Anna Hecht ◽  
Gary Butler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Model Comparison ◽  
Adult Height ◽  
Absolute Error ◽  
Average Error ◽  
Study Cohort ◽  
Prediction Errors ◽  
Growth Data ◽  
Short Children

Abstract Purpose To use machine learning (ML) to predict adult height (AH) based on growth measurements until age 6 years. Methods Growth data from 1596 subjects (798 boys) aged 0-20 from the longitudinal GrowUp 1974 Gothenburg cohort were utilized to train multiple ML regressors. Of these, 100 were used for model comparison, the rest was used for 5-fold cross-validation. The winning model, Random Forest (RF), was first validated on 684 additional subjects from the 1974-cohort. It was additionally validated using 1890 subjects from GrowUp 1990 Gothenburg cohort and 145 subjects form the Edinburgh Longitudinal Growth Study cohort. Results RF with 51 regression trees produced the most accurate predictions. The best predicting features were sex, and height at age 3.4-6.0 years. Observed and predicted AH were 173.9±8.9cm and 173.9±7.7cm, respectively, with prediction average error of -0.4±4.0cm. Validation of prediction for 684 GrowUp 1974 children showed prediction accuracy r=0.87 between predicted and observed AH (R²=0.75). When validated on the 1990 Gothenburg and Edinburgh cohorts (completely unseen by the learned RF model), the prediction accuracy was r=0.88 in both cases (R²=0.77). AH in short children was over-predicted and AH in tall children was under-predicted. Prediction absolute error correlated negatively with AH (p&lt;0.0001). Conclusions We show successful, validated ML of AH using growth measurements before age 6 years. The most important features for prediction were sex, and height at age 3.4-6.0. Prediction errors result in over- or under-estimates of AH for short and tall subjects, respectively. Prediction by ML can be generalized to other cohorts.

Sign in / Sign up

Export Citation Format

Share Document