scholarly journals Prediction of Physical Parameters of Pumpkin Seeds Using Neural Network

2017 ◽  
Vol 45 (1) ◽  
pp. 22-27 ◽  
Author(s):  
Bunyamin DEMIR ◽  
Ikbal ESKI ◽  
Zeynel A. KUS ◽  
Sezai ERCISLI
Keyword(s):  
Neural Network ◽  
Physical Properties ◽  
Intelligent Systems ◽  
Mean Squared Error ◽  
Simulation Analysis ◽  
Geometric Mean ◽  
Design Parameters ◽  
Physical Parameters ◽  
Pumpkin Seeds ◽  
Agricultural Materials

The design of the machines and equipment used in harvest and post-harvest processing should be compatible with the physical, mechanical and rheological characteristics of the fruits and vegetables. In machine design for agricultural products, several characteristics of relevant products and seeds should be known ahead. Designers can either measure all these design parameters one by one, or they may use intelligent systems to estimate such parameters. Neural networks (NNs) are new computational tools that provide a quick and accurate means of physical properties prediction of agricultural materials, and have been shown to perform well in comparison with traditional methods. In this research, some physical properties of pumpkin (Cucurbita pepo L.) seeds, including linear dimensions, volume, surface and projected area, geometric mean diameter and sphericity were calculated tridimensional in lab conditions. Then, prediction of these parameters was carried out using NNs. The research was divided into two parts; experimental investigation and simulation analysis with NNs. Back Propagation Neural Network (BPNN) and Radial Basis Neural Network (RBNN) structures were employed to estimate physical parameters of the pumpkin seeds. The Root Mean Squared Error (RMSE) was 0.6875 for BPNN and 0.0025 for RBNN structures. The RBNN structure was superior in prediction and could be used as an alternative approach to conventional methods.

scholarly journals Study of Physical Properties of Zea mays in the Development of Seed Metering Unit

2021 ◽  
Vol 14 (2) ◽  
Author(s):  
Ajay A.,
Keyword(s):  
Physical Properties ◽  
Surface Area ◽  
Geometric Mean ◽  
Static Friction ◽  
Friction Angle ◽  
Kernel Weight ◽  
Angle Of Repose ◽  
Design Parameters ◽  
Equivalent Diameter ◽  
Mean Values

The physical properties of seeds are very important to optimize the design parameters of various agricultural equipment used in their production, handling, and storage processes. Determination and use of these properties are also essential for the development of optimum seed metering mechanism and also in the design of a hopper for a planter for precise sowing of seeds. Physical properties such as length, surface area, breadth, roundness, equivalent diameter, sphericity, angle of repose, and coefficient of friction were determined for the development of the seed metering unit. The physical properties of seeds were calculated initially. Three varieties of maize seed Rasi-3033, NMH-589, and KMH-2589. The mean values of seed length, width, thickness, sphericity, geometric mean diameter, surface area, bulk density, coefficient of static friction, angle of repose, and thousand kernel weight were 11.00 mm, 7.75 mm, 4.58 mm, 0.65, 7.09 mm, 158.14 mm2, 746.4 kg m-3, 0.60, 28.17o and 0.23 kg, respectively. These properties were used in the development of efficient planter components to work effectively

scholarly journals Investigation of Some Physical Properties of Two Varieties of Sweet Potato (Ipomoea batatas (L.) Lam)

2021 ◽  
Vol 2 (1) ◽  
pp. 230-238
Author(s):  
Olufemi Adeyemi ADETOLA ◽  
Oluwatusin Seun ADENIYI ◽  
Deji Lawrence AKINDAHUNSI
Keyword(s):  
Stainless Steel ◽  
Physical Properties ◽  
Surface Area ◽  
Ipomoea Batatas ◽  
Geometric Mean ◽  
Galvanized Steel ◽  
Angle Of Repose ◽  
Sweet Potatoes ◽  
The Mean ◽  
Agricultural Materials

Physical properties of agricultural materials are essential in the development of machineries, equipment and devices. In this research, forty sample each of two unique varieties namely Jewel-orange flesh sweet potatoes (JOFSP) and Oriental-purple flesh sweet potatoes (OPFSP) physical properties were determined using standard methods and equations. The results show that JOFSP gave the mean length (110.68±24.59 mm), width(61.40±8.09 mm), geometric mean (39.72±8.19 mm), volume (187.78±73.85 ml), surface area (4950.00±203.32 mm2) and roundness (1.81±0.50) which were of higher values compared to that of OPFSP which gave the length (68.46±10.16 mm), width (59.32±5.82 mm), geometric mean (36.32±3.90 mm), volume (137.83±10.97 ml), surface area (4320.20±98.00 mm2) and roundness (1.41±0.30) respectively. JOFSP gave moisture content, thickness, mass, sphericity and true density of 58.00±10.17 %, 37.60±7.17 mm, 202.87±65.12 g, 0.35±0.08, and 1.17±0.27 g cm-3 which were of lower values compared to that of OPFSP which gave 79.32±3.84 %, 45.94±9.04 mm, 271.87±15.72 g, 0.53±0.08, and 1.89±0.14 g cm-3 for OPFSP respectively. The mean of the angle of repose and the static coefficient of friction considered for the three-separate surfaces namely plywood (9.35±2.87°, 0.17±0.05), stainless steel (8.50±3.50°,0.15±0.05) and galvanized steel (8.30±3.20°) of lower values for JOFSP compared to that of plywood which gave (11.80±2.25°, 0.21±0.04), stainless steel (9.90±2.02°, 0.19±0.05), galvanized steel (10.90±2.28°) for OPFSP while the coefficient static of friction of stainless steel for JOFSP gave a higher value of 0.20±0.13 compared to that of 0.17±0.04 for OPFSP respectively. These findings provide engineers with valuable information for designing different handling, grading, and drying systems for industrial processing.

scholarly journals Effect of moisture content on some physical properties of Canarium schweinfurthii Engl. fruits

2016 ◽  
Vol 62 (No. 4) ◽  
pp. 162-169 ◽  
Author(s):  
J.C. Ehiem ◽  
V.I.O. Ndirika ◽  
U.N. Onwuka
Keyword(s):  
Moisture Content ◽  
Physical Properties ◽  
Specific Surface ◽  
Surface Area ◽  
Specific Surface Area ◽  
Geometric Mean ◽  
Physical Parameters ◽  
True Density ◽  
Effect Of Moisture ◽  
Mass Volume

The effect of moisture content on some physical properties of three varieties of Canarium schweinfurthii Engl. fruits (small, large and long) was studied at 40.91%, 34.92%, 23.44%, 18.5% and 11.03% moisture content on wet basis in order to solve problems associated with designing and development of processing and handling equipment for these fruits. The physical parameters investigated were major, intermediate, minor diameters, geometric mean diameter, unit mass, volume, sphericity, density, bulk density, roundness, aspect ratio, porosity, surface and specific surface area. The results obtained showed that the physical parameters decreased linearly with a decrease in moisture content. Major diameter and true density of all the fruit varieties were not affected significantly (P < 0.05) by moisture content. Canarium schwein-furthii Engl. fruits are not round but spherical and oblong, hence, they can rather roll than slide. Among the studied varieties, small Canarium schweinfurthii Engl. is less bulky, has the highest specific surface area and is more porous.

scholarly journals Auto-Colorization of Historical Images Using Deep Convolutional Neural Networks

Mathematics ◽  
2020 ◽  
Vol 8 (12) ◽  
pp. 2258
Author(s):  
Madhab Raj Joshi ◽  
Lewis Nkenyereye ◽  
Gyanendra Prasad Joshi ◽  
S. M. Riazul Islam ◽  
Mohammad Abdullah-Al-Wadud ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
User Study ◽  
Mean Squared Error ◽  
Color Image ◽  
Machine Learning Techniques ◽  
Global Features ◽  
Black And White ◽  
Historical Images ◽  
Learning Techniques

Enhancement of Cultural Heritage such as historical images is very crucial to safeguard the diversity of cultures. Automated colorization of black and white images has been subject to extensive research through computer vision and machine learning techniques. Our research addresses the problem of generating a plausible colored photograph of ancient, historically black, and white images of Nepal using deep learning techniques without direct human intervention. Motivated by the recent success of deep learning techniques in image processing, a feed-forward, deep Convolutional Neural Network (CNN) in combination with Inception- ResnetV2 is being trained by sets of sample images using back-propagation to recognize the pattern in RGB and grayscale values. The trained neural network is then used to predict two a* and b* chroma channels given grayscale, L channel of test images. CNN vividly colorizes images with the help of the fusion layer accounting for local features as well as global features. Two objective functions, namely, Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), are employed for objective quality assessment between the estimated color image and its ground truth. The model is trained on the dataset created by ourselves with 1.2 K historical images comprised of old and ancient photographs of Nepal, each having 256 × 256 resolution. The loss i.e., MSE, PSNR, and accuracy of the model are found to be 6.08%, 34.65 dB, and 75.23%, respectively. Other than presenting the training results, the public acceptance or subjective validation of the generated images is assessed by means of a user study where the model shows 41.71% of naturalness while evaluating colorization results.

scholarly journals Analysis of the Physical Properties of Seeds of Selected Viburnum Species for the Needs of Seed Sorting Operations

Processes ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 711
Author(s):  
Zdzisław Kaliniewicz ◽  
Dariusz J. Choszcz
Keyword(s):  
Physical Properties ◽  
Ornamental Plants ◽  
Seed Mass ◽  
Terminal Velocity ◽  
Landscape Design ◽  
Physical Parameters ◽  
Regression Analyses ◽  
Uniform Size ◽  
Size Fractions ◽  
Physical Attributes

Viburnum is a genus of colorful and ornamental plants popular in landscape design on account of their high esthetic appeal. The physical properties of viburnum seeds have not been investigated in the literature to date. Therefore, the aim of this study was to characterize the seeds of selected Viburnum species and to search for potential relationships between their physical attributes for the needs of seed sorting operations. The basic physical parameters of the seeds of six Viburnum species were measured, and the relationships between these attributes were determined in correlation and regression analyses. The average values of the evaluated parameters were determined in the following range: terminal velocity—from 5.6 to 7.9 m s−1, thickness—from 1.39 to 1.87 mm, width—from 3.59 to 6.33 mm, length—from 5.58 to 7.44 mm, angle of external friction—from 36.7 to 43.8°, mass—from 16.7 to 35.0 mg. The seeds of V. dasyanthum, V. lentago and V. sargentii should be sorted in air separators, and the seeds of V. lantana and V. opulus should be processed with the use of mesh screens with round apertures to obtain uniform size fractions. The seeds of V. rhytodophyllum cannot be effectively sorted into batches with uniform seed mass, but they can be separated into groups with similar dimensions.

scholarly journals Physical properties and water absorption kinetics of three varieties of Mucuna beans

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ajibola B. Oyedeji ◽  
Olajide P. Sobukola ◽  
Ezekiel Green ◽  
Oluwafemi A. Adebo
Keyword(s):  
Physical Properties ◽  
Water Absorption ◽  
Rate Constant ◽  
Geometric Mean ◽  
Seed Mass ◽  
Activation Energies ◽  
Mucuna Pruriens ◽  
Absorption Kinetics ◽  
Kinetics Of ◽  
Soaking Temperature

AbstractThe physical properties and water absorption kinetics of three varieties of Mucuna beans (Mucuna pruriens, Mucuna rajada and Mucuna veracruz) were determined in this study. Physical properties including length, width, thickness, geometric mean diameter, sphericity, porosity, bulk density, area, volume and one thousand seed mass were calculated while hydration kinetics was studied by soaking Mucuna beans in water at 30 °C, 40 °C and 50 °C and measuring water uptake at 9 h interval. Peleg’s equation was used to model the hydration characteristics and Arrhenius equation was used to describe the effect of temperature on Peleg’s rate constant k1 and to obtain the activation energies for soaking. Significant variations were observed in almost all the physical properties of the different varieties, however, there were no significant differences (p < 0.05) in their thicknesses and bulk densities. The effectiveness of fit of Peleg’s model (R2) increased with increase in soaking temperature. Peleg’s rate constant k1 decreased with increase in soaking temperature while k2 increased with temperature increase. Activation energies of Mucuna pruriens, Mucuna rajada and Mucuna veracruz were 1613.24 kJ/mol, 747.95 kJ/mol and 2743.64 kJ/mol, respectively. This study provides useful information about the properties of three varieties of Mucuna beans that could be of importance to processors and engineers for process design and optimization.

scholarly journals Updated Estimates of Vitamin a Total Body Stores in Healthy Young Adults Determined by Compartmental Modeling with Vitamin a Intake Added as Data (FS06-07-19)

2019 ◽  
Vol 3 (Supplement_1) ◽  
Author(s):  
Jennifer Ford ◽  
Georg Lietz ◽  
Anthony Oxley ◽  
Joanne Green ◽  
Michael Green
Keyword(s):  
Young Adults ◽  
Vitamin A ◽  
Model Prediction ◽  
Simulation Analysis ◽  
Geometric Mean ◽  
Compartmental Analysis ◽  
Science Research ◽  
European Ancestry ◽  
Retinyl Acetate ◽  
Total Body

Abstract Objectives We applied a new modeling approach to generate estimates of vitamin A total body stores (TBS) for previously-studied subjects (Green et al. J Nutr 2016;146:2129–36) who were consuming moderate amounts of preformed vitamin A. Based on recent work, we hypothesized that inclusion of an estimate of vitamin A dietary intake (DI) during modeling would help compensate for the less-than-optimal study duration (14 d). Methods We reanalyzed retinol kinetic data collected after ingestion of [13C10]retinyl acetate by 26 young adults of European ancestry for whom estimates of DI were available. To predict TBS by compartmental analysis, geometric mean (GM) data on fraction of dose in plasma versus time plus estimated intake (2.9 µmol retinol activity equivalents/d) were analyzed using the Simulation, Analysis and Modeling software in light of previously-established models. We also used modeling to estimate coefficients (“FaS”) used in retinol isotope dilution (RID) equations and calculated TBS for the group and individuals. Results TBS predicted by the model without DI data included was 98 µmol; when the GM DI was included in the modeling data stream, predicted TBS was 273 µmol. Including DI data during modeling also resulted in lower predictions of intake [2.9 versus 8.7 µmol/d without DI, compared with the average RDA for adults (2.8 µmol/d)] and longer predicted days of vitamin A stores (125 versus 15 d). Using the FaS at 7 d (0.90) predicted by the model with DI, RID-predicted TBS agreed with the model prediction (GM, 274 µmol, range 106–889 µmol). Conclusions Results indicate that including an estimate of DI during modeling provides more realistic predictions of TBS for studies of short duration and improves confidence in model prediction of vitamin A status. Funding Sources Original human studies were supported by Biotechnology and Biological Science Research Council (grant BB/G004056/1 to GL) and Cancer Research UK; current analyses were supported by College of Health and Human Development, Penn State University.

scholarly journals Development of a Deep Neural Network Model for Estimating Joint Location of Occupant Indoor Activities for Providing Thermal Comfort

Energies ◽  
2021 ◽  
Vol 14 (3) ◽  
pp. 696
Author(s):  
Eun Ji Choi ◽  
Jin Woo Moon ◽  
Ji-hoon Han ◽  
Yongseok Yoo
Keyword(s):  
Neural Network ◽  
Thermal Comfort ◽  
Deep Neural Network ◽  
Mean Squared Error ◽  
Thermal Environment ◽  
The Body ◽  
Estimation Accuracy ◽  
Accurate Estimation ◽  
Body Parts ◽  
Joint Location

The type of occupant activities is a significantly important factor to determine indoor thermal comfort; thus, an accurate method to estimate occupant activity needs to be developed. The purpose of this study was to develop a deep neural network (DNN) model for estimating the joint location of diverse human activities, which will be used to provide a comfortable thermal environment. The DNN model was trained with images to estimate 14 joints of a person performing 10 common indoor activities. The DNN contained numerous shortcut connections for efficient training and had two stages of sequential and parallel layers for accurate joint localization. Estimation accuracy was quantified using the mean squared error (MSE) for the estimated joints and the percentage of correct parts (PCP) for the body parts. The results show that the joint MSEs for the head and neck were lowest, and the PCP was highest for the torso. The PCP for individual activities ranged from 0.71 to 0.92, while typing and standing in a relaxed manner were the activities with the highest PCP. Estimation accuracy was higher for relatively still activities and lower for activities involving wide-ranging arm or leg motion. This study thus highlights the potential for the accurate estimation of occupant indoor activities by proposing a novel DNN model. This approach holds significant promise for finding the actual type of occupant activities and for use in target indoor applications related to thermal comfort in buildings.

A Dynamic Model for the Design of Methanol to Hydrogen Steam Reformers for Transportation Applications

2004 ◽  
Vol 126 (2) ◽  
pp. 149-158 ◽  
Author(s):  
Gregory L. Ohl ◽  
Jeffrey L. Stein ◽  
Gene E. Smith
Keyword(s):  
Response Time ◽  
Dynamic Model ◽  
First Principles ◽  
Initial Conditions ◽  
Design Parameters ◽  
Physical Parameters ◽  
Steam Reformer ◽  
Powerful Means ◽  
Steam Reformers ◽  
Transportation Applications

As an aid to improving the dynamic response of the steam reformer, a dynamic model is developed to provide preliminary characterizations of the major constraints that limit the ability of a reformer to respond to the varying output requirements occurring in vehicular applications. This model is a first principles model that identifies important physical parameters in the steam reformer. The model is then incorporated into a design optimization process, where minimum steam reformer response time is specified as the objective function. This tool is shown to have the potential to be a powerful means of determining the values of the steam reformer design parameters that yield the fastest response time to a step input in hydrogen demand for a given set of initial conditions. A more extensive application of this methodology, yielding steam reformer design recommendations, is contained in a related publication.

Application of BP Neural Network into the Kow of Chemical Contaminants

2010 ◽  
Vol 121-122 ◽  
pp. 574-578
Author(s):  
Hui Yu Jiang ◽  
Min Dong ◽  
Wei Li
Keyword(s):  
Neural Network ◽  
Partition Coefficient ◽  
Bp Neural Network ◽  
Prediction Error ◽  
Rbf Neural Network ◽  
Physical Parameters ◽  
Bp Network ◽  
Chemical Contaminants ◽  
Water Partition Coefficient ◽  
Molecular Bond

The octanol / water partition coefficient (Kow) is an important physical parameters to describe their behavior in the environment. However, because of some reasons, it is difficult to determine the octanol / water partition coefficient of each compound accurately. In this paper, we will introduce RBF neural network and molecular bond connectivity index to forecast the solubility of organic compounds in water. The result is better using the BP network to predict, the correlation coefficient has achieved 0.998, the prediction error in the permission scope.

Sign in / Sign up

Export Citation Format

Share Document