Current feeding strategies aim to maximize efficiency at the pen level. However, feed intake varies across animals and in response to diet composition, making it difficult to capture these variations and control feeding effectively. A precision feeding system is required to feed animals individually, continuously monitor responses, and make timely adjustments to feed tailoring. Such a system would efficiently integrate dairy operations to enhance profitability and reduce their environmental footprint. Thus, the objectives of this dissertation were to build, test, and apply a precision feeding system able to tailor feeding strategies to animals more precisely and closely match their individual requirements. In Chapter 3, we describe the precision feeding system framework using directional data streams. The system integrates real-time farm data, segmented into data-analytic modules for independent testing and troubleshooting. It provides feeding instructions to automatic feeders and generates animal and financial monitoring reports. In Chapter 4, we describe the "Animal Performance" system module. This study developed a predictive model to estimate individual dry matter intake (DMI) by integrating markers, animal characteristics, dietary nutrient concentrations, and chewing sensor data. The performance of the developed model was then assessed and contrasted with the NASEM (2021) DMI equations. By incorporating covariates derived from short-term use of external and internal markers we demonstrated a greater accuracy of DMI predictions when using a fixed effects model, supporting its predictive capabilities for further application. In Chapter 5, we describe the "Diet Optimization" systems module, used to maximize profit by optimizing rations using a developed compact-vectorized version of NASEM (2021). The study aimed to simulate optimized diets, evaluate the economic impact of feeding individual diet, compare feed costs and income over feed cost (IOFC) for optimized group diet, and compare optimized diets against pen-averages (PEN). The results showed that IND diets had lower costs, higher milk production, and increased IOFC compared to CLU diets. Additionally, both IND and CLU diets outperformed PEN solutions. This work established methods for deriving efficient diet solutions for individual animals and using clustering techniques for more precise pen-level feeding. In Chapter 6, we describe the application of "Animal Performance", "Diet Optimization", and "Nutrient Titration" system modules. The former DMI model described in Chapter 4 was applied to the experimental data. The middle utilized optimized diets generated by the optimizer developed in Chapter 5, with additional algorithm updates. The latter aimed to investigate individual milk true protein production responses of dairy cows to varying levels of metabolizable protein (MP) and rumen-protected amino acids (RPAA) using automatic feeding systems and rank animals based on their individual gross milk protein efficiencies. Results demonstrated heterogeneous animal responses across MP and RPAA levels, ranging from linear, and quadratic to no response, emphasizing the necessity of addressing individual variability within a common pen. High-efficiency animals behaved consistently across MP treatments with lower variability, while low-efficiency animals showed high variability but consistently remained in the bottom efficiency rank. In conclusion, the precision feeding system underscores true capabilities to tailor nutrient delivery to individual cows, maximizing economic and environmental benefits, and sets the stage for future research focused on further refinement and automation of these technologies / Doctor of Philosophy / Feeding practices for dairy cattle have evolved significantly from manual grain mix offering to group feeding. While pen-level feeding has its benefits, it overlooks opportunities to maximize efficiency and minimize feed waste and nutrient excretion by not using individual animal variation to apply control feeding. With modern farms and increased technology adoption, feeding animals while being individually milked, even when group-housed, is now possible, leveraging this variability to apply precision feeding. In Chapter 3, we described the development of a precision feeding system that leverages technological advancements on dairy farms to gather and analyze data, supporting informed decision-making. This system includes various modules for testing and adjusting feeding strategies according to animal needs, providing feeding instructions to automatic feeders, and generating reports to help farmers monitor their animals and manage costs. Recognizing that precision feeding relies on quality data and accurate predictions of crucial metrics such as dry matter intake (DMI), Chapter 4 focused on developing a mathematical equation to predict DMI on an individual animal basis. This model demonstrated potential for commercial dairy operations due to its use of readily available farm-level predictors and its adequate performance compared to gold-standard field equations. Given the lack of efficient optimizers that incorporate individual animal data, in Chapter 5, we described the development of a new optimizer incorporated into the system to maximize profits. We simulated different feeding strategies, including optimized individual and group diets, and demonstrated that these tailored diets were more cost-effective and led to higher milk production compared to pen-average diets. To complete the development, testing, and application cycle, in Chapter 6, we applied the precision feeding system to determine the metabolizable protein (MP) requirements of dairy cows and assess milk protein production responses to different levels of MP and rumen-protected amino acids (RPAA). The results indicated varied responses among cows, highlighting the importance of individualized feeding to account for animal-to-animal differences within the same pen. Top-efficient animals were consistent in their responses across treatments, whereas bottom-efficient animals exhibited greater variability and consistently underperformed. In conclusion, the precision feeding system demonstrated significant potential to improve the efficiency of dairy farming by more accurately meeting the specific needs of dairy cattle. Future research will focus on refining this system and further automating the process for broader farm applications.

This thesis advances automated pig monitoring through novel machine learning approaches in behavior analysis, weight prediction and forecasting. For behavior analysis, we introduce a preprocessing framework that addresses data leakage in time series analysis through non-class-based windowing and chronological sampling, achieving up to 15% improvement in accuracy over conventional methods. For current weight prediction, we develop an automated pipeline using the Segment Anything Model (SAM) with deep learning, where our Xception-Net architecture achieves a mean absolute percentage error of 7.42%. For weight forecasting, we propose multi-input deep learning architectures combining spatial and temporal features, achieving a mean absolute percentage error of 5.56%. These methods demonstrate robust performance in real-world conditions while minimizing animal stress and manual labor requirements, contributing significantly to precision livestock farming practices. / Master of Science / Modern pig farming faces increasing pressure to efficiently monitor animal health and growth while ensuring high welfare standards. This research develops smart computer systems that can automatically track three important aspects of pig farming: how pigs behave, how much they currently weigh, and how much they will weigh in the future. Instead of requiring farmers to physically handle pigs for weighing or spending hours observing their behavior, our system uses cameras and sensors to collect this information automatically. We create new computer programs that can recognize different pig behaviors like eating, sleeping, and walking with over 95% accuracy. For weight monitoring, we develop a system using special depth-sensing cameras that can estimate a pig's weight within 7% of their actual weight, all without needing to move or disturb the animal. Looking ahead, our system can also predict future pig weights with over 94% accuracy, helping farmers make better decisions about feeding and care. These tools significantly reduce the time and effort needed for monitoring pigs while decreasing animal stress from handling. By providing accurate, real-time information about pig behavior and growth, this research helps farmers make better management decisions, ultimately leading to improved animal welfare and more efficient farming operations.

Current trends in agricultural equipment have led to an increasing degree of autonomy. As the state of the art progresses towards fully autonomous vehicles, it is important to consider assumptions implicit in the design of these vehicles. Current automation in harvesters have led to increased sensing and automation on current combines, but no published research examines the effect of machine size on the viability of the autonomous system. The question this thesis examines is: if a human is no longer required to operate an individual harvester, is it possible to build smaller equipment that is still economically viable? This thesis examines the appropriateness of automating these machines by developing a conceptual model for smaller, fully autonomous harvesters. This model includes the basic mechanical subsystems, a conceptual software design, and an economic model of the total cost of ownership. The result of this conceptual design and analysis is a greater understanding of the role of autonomy in harvest. By comparing machine size, machine function, and the costs to own and operate this equipment, design guidelines for future autonomous systems are better understood. It is possible to build an autonomous harvesting system that can compete with current technologies in both harvest speed and overall cost of ownership. / Master of Science

Nutritional management of dairy cattle is of importance to the industry due to its influence on production performance and association with large expenses for producers. Current ration formulation may be improved by predicting feeding recommendations for individual animals, rather than groups of animals, through precision feeding. Automated feeding systems (AFS) designed to deliver individual rations must include response-based models that utilize individual cow production data to make feed recommendations. These models require large data sets of individual cow responses to a variety of nutritional interventions. As a result, an experiment was designed to collect individual response data from 24 Holstein cows fed supplemental top dresses. After analyses, dry matter intake (DMI), milk yield (MY), milk fat yield, milk protein yield, feed efficiency, and activity were significantly affected by top dress (P < 0.001). These results suggest opportunity to use precision feeding to implement economically optimal ration recommendations designed to increase dairy cow production. Therefore, a second experiment was conducted in order to develop and test two algorithms that targeted individualized feeding to increase feed efficiency. Milk protein percentage (P = 0.008) and feed efficiency (P < 0.001) were significantly affected by a 3-way interaction between top dress, algorithm, and week. These results highlight the opportunity for precision feeding to increase the efficiency of individual dairy cows. Although the control group resulted in greater income over feed costs than either of the developed algorithm feeding strategies, algorithm refinement and modification may result in more efficient feeding recommendations that are economically viable. / Master of Science / Nutritional management of cattle is crucial to the dairy industry. The feeding of dairy cattle is the largest expense for producers and directly influences cow production. In particular, precision feeding of dairy cattle may have the ability to lower costs for farmers and increase the productivity of dairy cows. Currently, cattle are fed in group configurations, where cows with similar nutrient requirements are offered the same diet. However, individually feeding dairy cows utilizing precision technologies may have the ability to increase the production performance of cattle. Utilizing precision feeding to individually feed dairy cattle requires automated feeding systems (AFS) designed to decrease the additional labor associated with feeding animals as individuals. However, algorithms designed to predict individual animal nutrient requirements are lacking for use in AFS. As a result, large data sets of individual cow responses to varying diets are necessary to train algorithms designed to predict unique ration formulations for individual animals. Two experiments were developed to collect individual animal production responses that were used to develop two response-based algorithms capable of influencing feed efficiency of individual cows. The results from these experiments highlight the potential for precision feeding of dairy cattle to influence individual animal feed efficiencies and milk production. Future improvements in algorithm development and training are necessary in order for these feeding strategies to be economically worth the investment of AFS on commercial dairy farms.

The European honey bee, Apis mellifera, is an important pollinator of horticultural and agricultural field crops, providing ≈ 90% of all commercial pollination services (Genersch et al. 2010). The recent rise in colony loss due to Colony Collapse Disorder (CCD) has been a source of concern for both beekeepers and the apiculture industry. One of the factors implicated in CCD is infestation by the ectoparasitic mite, Varroa destructor. Initial efforts to control the mite relied heavily on regular application of miticides without regard to actual mite infestation levels. This approach has led to problems of resistance in the mite and contamination of the hive and hive-products. Because it is unlikely that miticides will be removed as an option for mite management, a precision mite management (PMM) approach using information on the spatiotemporal distribution of the mite to improve sampling and treatments is seen as a viable option, particularly with respect to treatment costs and impacts on the environment. The primary objective of this study was to develop an understanding of the spatiotemporal distribution of the Varroa mite and bee brood within hives for the purpose of developing a PMM approach for the mite. Varroa mite populations were sampled from May to June, 2012 and February to October, 2013. Sampling was conducted with three commonly used sampling methods: soapy water roll (SWR), brood uncapping, and a modified sticky board; brood uncapping, however, was discontinued during the study due to hive the labor cost and harmful effects of this method to the hives. Similar trends in mite population levels were observed using the soapy water roll and sticky board sampling methods. Spearman's nonparametric analysis showed that there was a significant correlation (ρ = 0.47, P<0.001) in mite population levels for the soapy water roll and sticky board methods for sampling conducted from February to September, 2013 (the SWR method was not used in October). This was despite the fact that there was no significant correlation (ρ= -0.03, P = 0.8548) between the two sampling methods during the spring sampling period from February to April, 2013. The observed lack of correlation between the two sampling methods in early spring was likely due to the low population of brood in the hive, which caused the majority of the mites to remain on adult bees. Mites per 100 adult bees, therefore, appear to reflect mite population levels within the hive more closely than mite fall on sticky borad during the February to April sampling period. This suggests that the soapy water roll method is a better method for estimating mite population levels within the hive in the early spring compared with the sticky board method. Geospatial analyses of the distributions of mite fall on the sticky boards were conducted using geostatistics and Spatial Analysis by Distance IndicEs (SADIE). Both analyses showed that mite fall on the sticky board was generally aggregated and the aggregation increased with mite population levels. The average range of the variogram from geostatistical analysis was estimated at 4 sticky board cells; this range value was increased to 5 cells and was used to develop a systematic outside-range sampling protocol for mites on a sticky board. The results showed that the accuracy of the systematic outside-range sampling compared well with that of the traditional sticky board counting method in estimating total mite fall, but required only 60% of the effort (i.e., counting 63 instead of 105 cells). SADIE analysis showed that there is an overall association between the distribution of mite fall on a sticky board and the distribution of brood within a hive. A greater degree of correspondence was also observed in the association of drone and mite distributions during May to June; greater correspondence in worker brood and mite associations was observed in August and September. These differences may be due to relative amounts of the two types of brood present within the hive. A test of the efficacy of precision application of Varroa mite treatment based on the association between drone brood and mite fall resulted in a significantly greater reduction in mite levels on the sticky board using a traditional miticide treatment method compared with the control and precision treatments (𝜒2 =362.571; df = 2; P <0.0001); mite population levels with the precision method, however, were significantly reduced compared with the control. / Master of Science in Life Sciences

The primary purpose of this study was to observe the relationship between muscle activation of the right hand with the force produced at the fingertips in an isometric precision pinch tracking task. Thirty right-handed subjects, 15 males and 15 females, with a mean age 23.5 (SD 3.5) years, free from any neurological disorder or physical ailment, had a pair of electromyography (EMG) electrodes placed over the first dorsal interosseous (FDI) muscle, which acts on the index finger, while performing a pinch force tracking task scaled to 20% maximum voluntary contraction (MVC). The tracking task was chosen because it created a continuously increasing force application to 20% MVC and then decreasing force release from 20% MVC at a prescribed rate in both cases of 6.66% MVC force per second. In addition to showing increases in EMG activation of the FDI with increases in force, the results revealed that muscle activation for a given force level was generally greater for force application than for force release. This may be due dynamics of muscle contraction or to patterns of multiple muscle coordination. / text

In the recent past precision farming has become increasingly popular amongfarmers. However, little has been done to study the business aspect of precision farming,with most research focusing on the production side. This purpose of this thesis is tostudy the feasibility of successfully opening and operating a precision farming firm inKentucky. To determine the feasibility of such a venture a computer model was createdand a producer survey was designed and distributed to farmers in Western and CentralKentucky.The purpose of the computer model was to determine the factors that wouldinfluence the successful operation of a precision farming firm including number of acresserviced per year, pricing of services, the cost of capital to borrow money, and manyother factors. A break-even analysis was performed to determine what kind of annualincreases in business would be required, what price range services should be in, and atwhat interest rate money could be borrowed and a simulated precision farming firm couldstill operate successfully.The producer survey was mailed to 336 farmers in Western and Central Kentuckybecause of their geographical locations and the type of crops that are grown there. Thesurvey response rate was 20 percent and of the 66 surveys that were returned 59 wereappropriate and useful for research. After compiling the results of the surveys,regressions were run to determine any correlation between dependent and independentvariables that affect the adoption rate of precision farming techniques. The results foundthat a negative correlation exists between age adoption rates of precision farming and thata positive correlation exists between farm size and adoption rates of precision farming.After conducting the research, it is believed that given the right economicconditions and management a precision farming firm is very capable of thriving inKentucky. However, the workforce must be very motivated and capable of constantlyrecruiting new clients to adopt precision farming.

The world population is projected to rise, and there is a growing concern of future food availability. Precision agriculture technologies are one solution to this problem as they aim to produce more food on less land. This study examines the adoption and intensity of precision agriculture technology usage by producers in North Dakota. Data from a North Dakota State University survey was collected and analyzed using an econometric double-hurdle model. Results of the study describe which producers adopt precision agriculture technologies, which technologies complement each other, and what affects the intensity of technology usage. Several technologies were found to have complementary effects on each other, larger farms are more likely to adopt PATs, and crop choices have varying impacts on the adoption and usage of PATs. Most of these findings agree with previous literature, although new light was shed on some new findings and predictions.

Recommender System (RS) has become one of the most important component for many companies, such as YouTube and Amazon. A recommender system consists of a series of algorithms which predict and recommend products to users. This report covers the selection of many open source recommender system projects, and movie predictions are made using the selected recommender system. Based on the predictions, a comparison was made between precision and an improved precision algorithm. The selected RS uses singular value decomposition in the field of collaborative filtering. Based on the recommendation results produced by the RS, the comparison between precision and the improved precision algorithms showed that the result of improved precision is slightly higher than precision in different cutoff values and different dimensions of eigenvalues. / Rekommendationssystem har blivit en av de viktigaste beståndsdelar för många företag, såsom YouTube och Amazon. Ett rekommendationssystem består av en serie av algoritmer som förutsäger och rekommenderar produkter till användare. Denna rapport omfattar valet av många öppen källkod rekommendationssystem projekt, och filmprognoser görs med det valda rekommendationssystemet. Baserat på filmprognoser, gjordes en jämförelse mellan precision och en förbättrad precision algoritmer. Det valda rekommendationssystemet använder singulärvärdesuppdelning som kollaborativ filtrering. Baserat på rekommendationsresultat som produceras av rekommendationssystemet, jämförelsen mellan precision och den förbättrade precisions algoritmer visade att resultatet av förbättrad precision är något högre än precision i olika brytvärden och olika dimensioner av egenvärden.

SyfteSyftet med denna studie var att undersöka passningsprecisionen hos ungdoms- och juniorishockeyspelare (15 – 18 år) som under den gångna säsongen var aktiva inom serierna ”Elit” eller ”Division 1” i antingen U16, J18 eller J20.MetodFör att undersöka passningsprecision i ishockey så designades två tester. Testerna gick ut på att försöka träffa en tre centimeter bred målpinne med en puck från ett avstånd på 15 meter. Fem spelare genomförde två test med olika komplexitetsnivåer, en i rörelse samt en stillastående. Varannan passning slogs med forehand och varannan med backhand. Passningarna genomfördes i serier om tio passningar (5 forehand och 5 backhand). På båda stationerna genomförde varje spelare fem serier, det vill säga totalt 50 passningar (25 forehand, 25 backhand).ResultatResultatet i denna studie visade att det fanns en signifikant skillnad i passningsprecisionen mellan forehand och backhand i såväl stillastående (p &lt; 0,001) som i rörelse (p = 0,009). Däremot var det ingen signifikant skillnad beroende av komplexitetsnivå för vare sig forehand (p = 0,29) eller backhand (p = 0,22).SlutsatserUtifrån det resultat som framkom så kan man se att passningshållet (forehand/backhand) påverkar passningsprecisionen. Samtliga spelare hade en högre precision på sin forehandsida jämfört med backhand oberoende av komplexitetsnivå. / PurposeThe purpose of the study was to measure passing precision among youth- and junior ice hockey players between 15 and 18 years of age, who in the past season played at either “elite” or “Division 1” level in U16, J18 or J20.MethodsTo measure passing precision in ice hockey, two tests were designed. The tests consisted of a player trying to hit a three-centimeter-wide pin by passing a puck from 15 meters away. Five players did the test that were divided into two different levels of complexity, one in forward motion and one standing still. The players hit a total of ten passes divided into five forehand passes and five backhand passes, they took turns in hitting forehand and backhand one by one. In total, the players did five series of ten passes on each station, a total of 50 passes divided into 25 forehand passes and 25 backhand passes.ResultsThe result of this study showed that there was a significant difference in passing precision between forehand passes and backhand passes, regardless off whether the pass was played in motion (p = 0,009) or standing still (p &lt; 0,001). However, the test did not show any significant difference between the different levels of complexity on either forehand (p = 0,29) or backhand (p = 0,22).ConclusionsBased on the results from this study, you can see that the way you hit the pass (forehand/backhand) effects the passing precision. All players had a higher precision on their forehand than their backhand, regardless of level of complexity.