Indiana University-Purdue University Indianapolis (IUPUI) / Detecting crop rows from video frames in real time is a fundamental challenge in the field of precision agriculture. Deep learning based semantic segmentation method, namely U-net, although successful in many tasks related to precision agriculture, performs poorly for solving this task. The reasons include paucity of large scale labeled datasets in this domain, diversity in crops, and the diversity of appearance of the same crops at various stages of their growth. In this work, we discuss the development of a practical real-life crop row detection system in collaboration with an agricultural sprayer company. Our proposed method takes the output of semantic segmentation using U-net, and then apply a clustering based probabilistic temporal calibration which can adapt to different fields and crops without the need for retraining the network. Experimental results validate that our method can be used for both refining the results of the U-net to reduce errors and also for frame interpolation of the input video stream. Upon the availability of more labeled data, we switched our approach from a semi-supervised model to a fully supervised end-to-end crop row detection model using a Feature Pyramid Network or FPN. Central to the FPN is a pyramid pooling module that extracts features from the input image at multiple resolutions. This results in the network’s ability to use both local and global features in classifying pixels to be crop rows. After training the FPN on the labeled dataset, our method obtained a mean IoU or Jaccard Index score of over 70% as reported on the test set. We trained our method on only a subset of the corn dataset and tested its performance on multiple variations of weed pressure and crop growth stages to verify that the performance does translate over the variations and is consistent across the entire dataset.

The structure and payload of a CubeSat flight experiment that investigates the performance of particle dampers in a micro-gravity environment was designed, built, and tested, and will provide on orbit data for model validation and improved performance predictions for space applications of particle damping. A 3-D solid model of the integrated CubeSat structure and payload was created satisfying all constraints from CubeSat and the System Dynamics Department at Northrop Grumman Aerospace Systems. The model was verified using commercially available Finite Element Analysis software (FEA), and a prototype structure part was fabricated. The prototype was tested and verified the FEA. A complete subassembly ready for flight was manufactured as an engineering unit and tested to space qualification loads of both launch vibration and thermal vacuum. Two additional units were contracted out for manufactured to serve as the flight unit and backup, and are currently ready for launch.

Noncompliance in students with Emotional/Behavioral Disorders (EBD) can contribute to difficulty with peer and teacher relationships and may result in reduced time for academic instruction. The Precision Request, an intervention which uses alpha commands, verbal praise, and reductive consequences, has been shown to increase compliance in students with EBD, but no studies have accounted for which component is responsible for the change. This study used an ABCDAX add-in component analysis to determine which component of the Precision Request produced the most effect on behavioral compliance in five sixth-grade elementary students with EBD. Data were collected on percent of student compliance, latency to compliance, and teacher and paraprofessional use of verbal praise and reductive consequences. Percent of correct implementation of the Precision Request was also recorded. All data were subsequently inspected via visual analysis. The interventionists which participated in the study were unable to implement the Precision Request with fidelity and no effect was found on student compliance, which prompted researchers to examine characteristics of the interventionists as a possible explanation for failure to implement with fidelity. A comparison of interventionists suggests that the Precision Request may be too difficult to implement for an individual who lacks behavioral training, who does not use foundational classroom procedures such as positive reinforcement and verbal praise, and/or whose philosophical viewpoints are not conducive to behavior analysis. Future research should examine contextual fit as regards behavioral interventions and interventionists, as well as which behavioral principles need to be mastered by an interventionist before the Precision Request can be implemented with fidelity.

Purpose: Knowledge of breast cancer genetics is critical for those at increased risk whomust make decisions about breast cancer screening options. The purpose of this study was toexplore cognitive and emotional variables that might influence knowledge of breast cancergenetics.Methods: This descriptive, exploratory study analyzed theory-based relationships amongvariables related to knowledge of breast cancer genetics in cancer families. Participants includedfirst-degree relatives of women with breast cancer who had received genetic counseling andtesting; participants themselves did not have breast cancer and had not received geneticcounseling or testing. Data were collected by telephone interview and survey. Variables analyzedinclude numeracy, health literacy, cancer-related distress, age, education, and the reportedamount of information shared by the participants family members about genetic counseling.Results: The multiple regression model explained 13.9% of variance in knowledge of breastcancer genetics (p = 0.03). Best fit of the multiple regression model included all variables excepteducation. Reported amount of information shared was the only independently significantpredictor variable (p = 0.01).Conclusion: Participants who reported higher levels of information shared by a familymember about genetic counseling also demonstrated increased knowledge about breast cancergenetics.

Purpose: Knowledge of breast cancer genetics is critical for those at increased risk whomust make decisions about breast cancer screening options. The purpose of this study was toexplore cognitive and emotional variables that might influence knowledge of breast cancergenetics.Methods: This descriptive, exploratory study analyzed theory-based relationships amongvariables related to knowledge of breast cancer genetics in cancer families. Participants includedfirst-degree relatives of women with breast cancer who had received genetic counseling andtesting; participants themselves did not have breast cancer and had not received geneticcounseling or testing. Data were collected by telephone interview and survey. Variables analyzedinclude numeracy, health literacy, cancer-related distress, age, education, and the reportedamount of information shared by the participants family members about genetic counseling.Results: The multiple regression model explained 13.9% of variance in knowledge of breastcancer genetics (p = 0.03). Best fit of the multiple regression model included all variables excepteducation. Reported amount of information shared was the only independently significantpredictor variable (p = 0.01).Conclusion: Participants who reported higher levels of information shared by a familymember about genetic counseling also demonstrated increased knowledge about breast cancergenetics.

Microelectronic Measuring Systems (MEMS) are being used to capture kinematic data in real-world environments. The benefits of using MEMS are their small size, relatively low cost (compared to an Optical Motion Capture System) and the ability to capture real-time data in almost any environment. The accuracy and precision of MEMS can be influenced by elements in their surrounding environment such as building materials (i.e., reinforced steel) and structural components (i.e., elevators). Recognizing the influence of the environment on MEMS output is important if the MEMS are to be used in real-world environments where subjects could navigate between various environments. MEMS can also be affected by dynamic motion therefore testing of the MEMS in the same conditions in which they are to be used will help to identify any issues prior to data collection. The overall purpose of this thesis was to determine if the outputs of four Shimmer 2r MEMS were accurate and precise enough in static and dynamic conditions to use in a future study to assess gait activities of daily living in individuals with a unilateral transtibial amputation. In order to understand the effect of the environment on the MEMS, accuracy and precision were assessed in a rural environment (to reduce the effect of building materials and structural components) as well as the clinical environment where they will eventually be used for research. The MEMS were also evaluated in static and dynamic conditions to better understand how motion affected accuracy and precision. The results of this study confirmed that the clinical environment affected the MEMS outputs. During the dynamic condition, the gyroscope output of one MEMS sensor was significantly different than the other devices indicating recalibration or possible exclusion from future studies. Prior to using MEMS in research, it is advisable to investigate the effects of the environment on the sensor outputs as well as assess the performance of the individual sensors. / Thesis / Master of Science Rehabilitation Science (MSc) / The overall objective of this thesis was to determine if four Shimmer 2r Microelectronic Measuring Systems (MEMS) were accurate and precise enough in static and dynamic conditions prior to their use in a future study to assess seven activities of daily living (including level walking, ramp walking and stairs) in individuals with a unilateral transtibial amputation in a clinical environment. To understand the effect the environment has on the MEMS, they were assessed in both a rural environment to reduce the effect of building materials, as well as the clinical environment where they will eventually be used for research. This study confirmed that the clinical environment affected the MEMS outputs, although these effects were deemed to be clinically insignificant for the intended purpose of these MEMS. Calibration as well as accuracy and precision assessment of MEMS should be executed in the conditions and environments in which they are to be utilized.

<p> This thesis describes a new method to measure high direct voltage of the range of 100 KV to 200 KV with very high accuracy. The principle, based on the capacitive divider method, is presented in the first part. </p> <p>This thesis is, however, principally concerned with the design of the low voltage capacitor of the divider and its accuracy. The investigations made lead to an instrument having the accuracy required, which is 0.1 parts per million. </p> / Thesis / Master of Engineering (MEngr)

Internet of Things (IoT) has drawn much attention in recent years. With IoT, physical world entities get connected through internet. IoT is used currently in various applications, such as environmental monitoring, control systems, farming, home automation, security and surveillance systems etc. The aim of this research is to design a low-cost, energy-efficient, reliable and scalable embedded application for the smart greenhouse monitoring system. The IoT based system designed in this thesis uses various sensors to measure the air and soil quality parameters in the greenhouse, and monitor real-time data online using web-server and mobile phone based applications. A ZigBee based wireless sensor network is implemented to transport various sensory data to the gateway. Among other contributions, the designed system develops a new routing algorithm by introducing a confirmed delivery of packets and re-routing features. We also introduced an efficient cost metric for making routing decisions within WSN using hops count, and simple bi-directional link quality estimator using PRR and current battery voltage of neighbor nodes. We also verified the stability of the system by conducting various performance tests. The system is equipped with data analytic functions for the online examination of the data. The designed system adopts event-based triggering and data aggregation methods to reduce the number of transmissions, and develops a new algorithm for such purpose. The web-server and mobile applications have user interface to display the output of the data analytic services, warning, control operations and give access to query data of the user's interest.

Growing winter cereal cover crops (WCCCs) has been identified as an effective in-field practice to reduce nitrate-nitrogen (N) and total phosphorus (P) losses to Upper Mississippi River Basin, USA. In this region, however, growers are reluctant to plant WCCCs prior to corn (Zea mays L.) due to soil N immobilization and corn establishment issues. Two strategies to minimize these issues are (i) incorporating legumes and brassicas into WCCCs as mixtures and (ii) precision planting of cover crops. The objective of chapter 1 was to (i) evaluate the effect of cover crop mixtures vs a no-cover crop control on soil health indicators and (ii) assess the impact of precision planting of cover crops on soil nutrient availability, soil nutrient stratification, soil permanganate oxidizable carbon (POXC) and soil organic carbon (SOC) stocks “on” and “off” the corn row over three depths (0-5, 5-20, and 20-90 cm). Treatments were (i) a no-cover crop control (NCC); (ii) no cover on corn row, hairy vetch (V) on middle row, and winter cereal rye (WCR) on the outside row of corn (NOVR); and (iii) oats (Avena sativa) and radishes (Raphanus sativus) on the corn row, V on the middle row, and WCR on the outside row (ORVR). Our results indicated NCC had lower SOC stocks than the NOVR and ORVR only at 0-5 cm depth. Soil POXC was more sensitive to cover crop management than SOC, and POXC concentrations were higher in ORVR at 5-20 cm than the NCC control. At 0-5 cm depth, cover cropping increased Bray-1 soil test P (STP). Soil test P declined over depth reflecting its immobility in the soil. Mehlich-3 soil test K (STK) was higher in cover crop treatments than the no-cover crop control at 0-5 cm depth. Soil test K was higher on corn row indicating that the oats and radish mix and corn residue decomposition releases K detectable in soil as Mehlich-3 K. Soil test sulfur was similar among treatments but higher at 20-90 cm depth reflecting S leaching and/or potential anion exchange capacity at depth that can lead to subsoil sulfate-S accumulation. These results indicate cover cropping in the fragipan belt / Alfisols of the Upper Mississippi River Basin can benefit soil after six years, but soil C benefits are limited to surface soil depths.In Chapter 2 the objectives were to (i) evaluate the biomass, nutrient concentration, and uptake of precision planted cover crop mixtures; (ii) assess whether precision planted cover crops influence corn stand density, grain yield, yield components, and nutrient balances; identify the best economically viable precision planted mixture prior to corn. Treatments were (i) a no-cover crop control (NCC); (ii) no cover on corn row, hairy vetch (V) on middle row, and winter cereal rye (WCR) + annual rye (AR) on the outside row of corn (RVSKIP); and (iii) no cover on corn row, clover (C) on the middle row, and WCR + AR on the outside row (RCSKIP). Results indicated that RVSKIP was always high yielding, with high N uptake, and low C:N ratio (25) suggesting it could release N throughout the corn growing season without immobilizing N. Cover crops influenced corn population only in one site-yr but that did not result in lower corn grain yield reflecting corn potential for filling the plant gap by creating larger ears with heavier grain (TKW). Similar corn grain in all cover crop treatments was mainly due to adding optimum N as fertilizer. We concluded that overall, cover cropping could benefit soil over a six-year period but to optimize their benefit to corn, adjustments to N should be made. Therefore, future research should focus on revisiting corn N requirement especially in cover crop mixtures with high percentage (>50%) of legumes in the mixture to determine the fertilizer value of the cover crops.

No description available.