Approaches to Precision Animal Feed Production using Hyperspectral Imaging and Computational Intelligence

( Daniel Dooyum Uyeh ),( Yushin Ha ) 한국농업기계학회 2019 한국농업기계학회 학술발표논문집 Vol.24 No.2

A resilient animal industry will require cost-effective feed rations as feed accounts for between 60 to 80% of production costs. Owing to the complexities in feed formulation, software programs are of benefit in ensuring accurate nutrient compositions with selections of cost-efficient materials. However, requirements of specialized techniques for users, high computing power needs, and lack of user-software interactivity for optimizing results, for example, limit current feed formulation software use. Researchers have been exploring the possibility of using food industry and agricultural by-products, and food waste in feed formulation with the benefits of reducing feed deficits and costs. The nutrient profiles of by-products and food wastes, however, are highly variable due to inconsistency in sources and extraction methods. To address these gaps, software and hyperspectral imaging models were developed. Subsequently, the developed systems were integrated into existing ones to propose two models for precision livestock feed production.

Optimization of Total Mixed Ration (TMR) feed formulation for Cattle Using Evolutionary Systems

( Uyeh Daniel Dooyum ),( Rammohan Mallipeddi ),( Trinadh Pamulapati ),( Tusan Park ),( Junhee Kim ),( Seungmin Woo ),( Yushin Ha ) 한국농업기계학회 2017 한국농업기계학회 학술발표논문집 Vol.22 No.2

Different food products obtained from cattle are important sources of nutrients to humans worldwide. About 60~80% of production cost is incurred by animal feed which is dependent on the class and phase of the animal. This is a non-deterministic polynomial-time hardness (NP-hard) recurrent problem due to the existence of both linear and non-linear constraints. For most programming tools, satisfying constraints at specific stages of breeding are often not possible. This entails the advancement of a program that has an intrinsic mechanism to allow easing of constraints based on the necessities of it's users. Consequently, the formulation of the problem and system of optimization should facilitate this. We modified the conventional formulations using parameters that allows tolerance that accommodate constraints slackening and proposed a method exploring evolutionary systems. Results of our experimental trials indicated that easing requirements has direct connections with the cost and in some instances quantity of the feed. We propose a system which possesses the capability to explore for a feasible and least cost result if available or the best solution if otherwise and find the suitable components to be used in the formulation.

Trends in Automation and Robotics in Protected Horticulture

( Uyeh Daniel Dooyum ),( Senorpe Asem-hiablie ),( Tusan Park ),( Seungmin Woo ),( Hoseo Lee ),( Junhee Kim ),( Yushin Ha ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.2

Changes in climate and associated negative impacts on production agriculture have increased the focus on adaptation strategies including protected cultivation systems. Incorporation of automation and robotics in such systems provide additional benefits such as reduced exposures to chemicals that are harmful to human operators in these enclosed structures. Also, environmentally-friendly practices such as precision weed control which reduce the use of chemicals are made possible by machine vision. Moreover, automation provides opportunities for improved positioning in the global market through increased production. In addition to a review of published reports on automation and control in production systems, five state-of-the-art greenhouses and a major international industry exhibition were visited in order to examine trends in protected cultivation. Data on automation systems and production outputs were collected and analyzed. Our findings show that important gains have been made recently including substantial progress in the development of robots for protected cultivation in greenhouses. For example, 5,000 kg/ha of paprika with 1,500,000 growth lines was cultivated in a state-of-the-art greenhouse using a workforce of 50 personnel compared to 2500 kg/ha in the open field with a considerably higher labor force. This represented a 50% increase in production per square meter and indicates some of the opportunities presented by protected cultivation in meeting growing demands without increasing areas under cultivation. Greenhouse cultivation could be a major driver in attaining food security especially in countries most susceptible to changes in climate. There is a need therefore for improvements in systems as well as the development of relatively affordable technology to facilitate automation.

Greenhouse layout optimization enhances safe and rapid robot navigation

( Daniel Dooyum Uyeh ),( Rammohan Mallipeddi ),( Tusan Park ),( Junhee Kim ),( Yeongsu Kim ),( Seokho Kang ),( Yushin Ha ),( Seungmin Woo ) 한국농업기계학회 2020 한국농업기계학회 학술발표논문집 Vol.25 No.1

Protected systems such as greenhouses provides opportunities such as increasing production and ease in environmental regulation required for optimal plant growth. However, problems such as poor ventilation in greenhouses can be fatal to the human workforce. This has led to research to develop robots for hazardous tasks. It is difficult to predict at which point a robot will need to return to the start point; to offload or refill for transportation and spraying schedules respectively or charge the battery for all category of robots. It will be commercially constraining to manufacture robots for every greenhouse specification. this study, greenhouse layout optimization problem was formulated to find optimal points on each bed to create an access path that would enable reduction in travel time from any point in the greenhouse to the base point. The optimization problem was solved using Differential Evolution (DE), an Evolutionary Algorithm. The system considers - a) required space for inter-bed and rotary robot navigation b) standard bed specification, c) area of the greenhouse, d) base point for robot starting and termination. The above parameters can be changed to user preference.

Appraisal of thin layer drying rate of parboiled rice applying different Mathematical models

( Uyeh Daniel Dooyum ),( Seung Min Woo ),( Md. Kamruzzaman ),( Yu Shin Ha ) 한국농업기계학회 2016 한국농업기계학회 학술발표논문집 Vol.21 No.2

Rice is a staple food for more than half of the World`s population. A lot of post-harvest losses is currently accrued due to less understanding of drying rate by most rice processors especially in developing countries. These includes moisture content where high temperature drying should be stopped, tempering should be done, gentle drying to milling moisture content, etc. A proper understanding of drying rate of rice will go a long way in solving a lot of issues involved with drying of this grain. This study treated Japonica rice with initial moisture content of 14.3% using the parboiling method. This increased the moisture content to a final moisture content after treatment of 28.3%. With the use of a circulatory drying oven, this study determined the reduction in drying weight in real time using Aduino software. Different selected empirical models were then used to simulate tests of thin layer drying data at the optimal temperature of drying rice. Appraisal of the mixt mathematical models using the F-Statistic showed that modified Henderson & Pabis`s (MR= A exp [Bt] + C exp [-Dt] + E exp [Ft]) and Henderson & Pabis`s (MR = A exp [Bt]) as the best models with value of 5944.54 and 4548.64 respectively. amongst all the tested empirical models, Two-term expotential (MR = A exp [Bt] + [1 - A] exp a exp [Bat]) had the least F-statistic value of 26.47. Analysis of data showed constant drying rate to occur between 0-250 minutes with the best models. The best empirical equations enabled writing of mathematical expressions for the drying rate and time.

Precision Livestock Feed Production Using Dynamic Approaches

( Uyeh Daniel Dooyum ),( Rammohan Mallipeddi ),( Trinadh Pamulapati ),( Tusan Park ),( Seungmin Woo ),( Junhee Kim ),( Yushin Ha ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.2

Increasing human populations are leading to increasing and sometimes conflicting demands on land and resources. Agriculture, particularly the livestock industry will need to increase productivity using existing or fewer resources to meet demands. A resilient livestock industry will require cost-effective feed rations as feed accounts for between 60 to 80% of production costs. Techniques in computational intelligence were used in coding and fine-tuning algorithms for feed formulation. Simulations were done in MATLAB to evaluate the performance of the algorithms. Hyperspectral imaging and near infrared spectroscopy were used to acquire spectral data from mixed by-products and packaged feed. Preprocessing methods such as second derivative and normalization were applied to the data to remove noise. Data was acquired from a spectral range of 900 to 2100 nm. Prediction tools (Partial least square regression and Unscrambler) were used to build amino acids, sugars, organic acids and moisture content models. This presents rapid, non-destructive measurements with no sample preparation and high sensitivity. All the models had satisfactory R² values. Subsequently, the developed systems were combined with existing systems to propose models for precision livestock feed production.

Interactive livestock feed ration optimization using evolutionary algorithms

Dooyum, Uyeh Daniel,Mallipeddi, Rammohan,Pamulapati, Trinadh,Park, Tusan,Kim, Junhee,Woo, Seungmin,Ha, Yushin Elsevier 2018 Computers and electronics in agriculture Vol.155 No.-

<P> The profitability of the livestock industry largely depends on cost-effective feed ration formulation as feed accounts for between 60 and 80% of production costs. Therefore, feed formulation is a recurring problem for breeders. In addition, the presence of linear and non-linear constraints, and multiple possible combinations that are subject to upsurge makes the formulation of feed a Non-deterministic Polynomial-time hard (NP-hard) problem. Generally, feed formulation is done by specifying the nutritional requirements as rigid constraints and an algorithm attempts to find a feasible cost-effective formulation. However, relaxing the constraints can sometimes provide a huge reduction in the cost of feed while not seriously affecting the economic performance of the livestock. This entails the development of a feed formulation software that has an inbuilt mechanism to enable relaxation to the constraints based on the users’ necessities. Accordingly, the problem formulation and the optimization algorithm should facilitate this. We modified the conventional problem formulation with a tolerance parameter (as a percentage of the actual value) to accommodate the relaxation of constraints. We solved this problem with differential evolution, a variant of evolutionary algorithms, which are good for handling NPhard problems. In addition, the relaxation of the constraints was done in an interactive way using the proposed method without penalties. In other words, the proposed method is flexible and possesses the ability to search for a feasible and least-cost solution if available or otherwise, the best solution and finds the suitable feed components to be used in ration formulation at an optimal cost depending on the nutrient requirements and growth stage of the animal. </P>

Internet of things in animal feed production process: taking feed production to the next level

( Daniel Dooyum Uyeh ),( Hyunggyu Park ),( Yeongsu Kim ),( Seokho Kang ),( Yushin Ha ),( Seungmin Woo ) 한국농업기계학회 2021 한국농업기계학회 학술발표논문집 Vol.26 No.1

The major cost of animal production is attributed to feed with a recorded 60 to 80% of the total production cost. For efficient and sustainable animal production, special attention needs to be given to feed production. Feed production involves many processes. This includes feed intake, storage, grinding or cutting, mixing, and transportation. The improper management of these processes as currently recorded in many feed production factories around the world has led to increased production cost and invariably cost of animal products that are vital to human nutrition and many industries. There are well-developed and adopted algorithms and systems for animal feed formulation and production. However, most of these systems are not synchronized, thus leading to inefficiency in the total system. The internet of things (IoT) which is about creating an internet within a factory will be beneficial in connecting all the complex processes in animal feed production. In this study, we propose a smart factory system where all the processes from receiving raw materials, to storage, mixing, packaging, batching, loading out, and delivery to the farms are connected and data is fed back to a central server. This would enable operators to see in real-time the entire process and improve decision-making.

Variations in components of feed materials for livestock production

( Daniel Dooyum Uyeh ),( Yeongsu Kim ),( Hyuntak Kim ),( Seungmin Woo ),( Seohkho Kang ),( Hyunggyu Park ),( Yonggik Kim ),( Yushin Ha ) 한국농업기계학회 2022 한국농업기계학회 학술발표논문집 Vol.27 No.1

The local and global demand for livestock products such as milk, beef, and cheese is recorded. This trend is projected to double by 2050 compared to the 2012 levels. Various factors could be attributed to this trend, such as the demand for foods that are rich in protein content. Up to 33% of the protein and 17% of the global kilocalorie intake is currently supplied by the livestock sector for the global human population, which is currently at 7.2 billion people. Improved standards of living and changes in social habits are other reasons. Feed, which accounts for 60 to 80% of the production cost, is a major expense in livestock production. Research has been focused on cost-effective and sustainable feed production over the years. A sustainable livestock industry would heavily rely on precision in feed production, which is vital. In this study, we examined the extent of variation in nutrient composition of feed materials by examining the materials for; a) variation within livestock feed factories; b) similar materials amongst different livestock feed factories; and c) finished livestock feed and the labeled content. Results showed a significant variation of up to 20% in the nutrient content of the livestock feed materials and the finished livestock feed. This variation could cause serious adverse effects on the productivity of the animals and the cost of breeding.

Optimizing Quality Parameters of Japonica Type Rice using Parboil System

( Uyeh Daniel Dooyum ),( Seung Min Woo ),( Dong Hyuck Hong ),( Yu Shin Ha ) 한국농업기계학회 2015 한국농업기계학회 학술발표논문집 Vol.20 No.2