University of Idaho Library Digital Initiatives
Not a member yet
54971 research outputs found
Sort by
Using Remote Sensing Data to Model Habitat Selection and Forage Quality for Herbivores in High Northern Latitudes in a Changing Climate
No full textLandscapes located in high northern latitudes (≥ 60°N) are changing at a rate two to three times the global mean. Research is needed to assess the current state of northern latitude regions to best identify the impacts of climate change, which can inform the advancement of policies and management strategies. In response to warming induced landscape changes, management agencies are identifying practical “adaptive strategies” that may mitigate the negative effects of climate change. One such strategy in wildlife management is to evaluate and enhance monitoring programs, and to consider incorporating new tools to augment monitoring efforts. Geospatial tools are one set of technologies that may enhance evaluation and monitoring for wildlife management. These tools enable spatial data to be collected, analyzed, and visualized in ways that assist in planning and management activities. Two common geospatial tools used in wildlife management are (1) mobile Global Positioning Systems (GPS) that can be housed in collars worn by a variety of species, and (2) remote sensing, which collects noncontact information regarding the physical and biological characteristics from a given target using reflected or emitted radiation. The second chapter of this dissertation incorporates remotely sensed products in conjunction with GPS-telemetry from four Alaska moose populations to assess how habitat selection changes in response to increased temperatures. Both male and female moose in all populations increasingly, and nonlinearly, selected for denser canopy cover as ambient temperature increased during summer, where initial increases in the conditional probability of selection were initially sharper then leveled out as canopy density increased above ~50%. However, the magnitude of selection response varied by population and sex. In two of the three populations containing both sexes, females demonstrated a stronger selection response for denser canopy at higher temperatures than males. We also observed a stronger selection response in the most southerly and northerly populations compared to populations in the west and central Alaska. The third and fourth chapters of this dissertation explore the development of remote sensing approaches to characterize, monitor, and map forage quality in high latitude regions of Alaska. I used hyperspectral data in conjunction with plant structural metrics derived from digital photographs and unmanned aerial vehicle structure from motion photogrammetry. My results suggested that spectral vegetation indices calculated from hyperspectral remote sensing are an appropriate method for estimating important forage quality metrics such as dietary fibers (Chapter 3) – hemicellulose, cellulose, neutral detergent fiber, acid detergent fiber, acid detergent fiber, and silica – as well as integrated forage metrics (Chapter 4) – digestible protein and dry matter digestibility. My results also indicated that incorporating shrub structure is an important, and often unconsidered, aspect of remotely sensed forage quality metrics.doctoral, Ph.D., Natural Resources -- University of Idaho - College of Graduate Studies, 2020-1
A Stateless Broadcast Network Protocol for LoRa
No full textIn this thesis a Stateless Broadcast Network Protocol for LoRa (SBNPL) is proposed. Simulations of the protocol were done for validation of the algorithms using the ns-3 simulation software and ns-3 Lora Module (NLM). The result is a viable broadcast protocol that can be used on low cost Long Range (LoRa) devices to create a reliable, secure, and easily deployed sensor network. For busy locations with many LoRa devices the amount of data, while limited, can fall within the regional duty cycle and dwell time for LoRa devices.masters, M.S., Computer Science -- University of Idaho - College of Graduate Studies, 2020-1
On Task Allocation in Mobile Edge Computing with a Focus on Machine Learning Applications
No full textMobile Edge Computing (MEC) is proving to be a very successful alternative to cloud computing (CC) for executing computationally intensive tasks that cannot be handled by end devices such as laptops and smart phones. The MEC paradigm facilitates task computation at the edge of the network rather than the cloud. It has been shown that MEC decreases delay and energy consumption while simultaneously reducing the load on backbone networks and the clouds. The hierarchical-MEC (H-MEC) paradigm adds on to MEC by involving idle end devices in the task computation process. H-MEC can offer the advantages of MEC, while further reducing the load on edge networks and edge servers. A large proportion of edge computing tasks comprise some form of data analytics where there is an increasing trend to use machine learning (ML) techniques. Therefore, in order to share the burden of complex ML algorithms and to preserve data privacy, employing the ML training in a distributed manner on end devices or learners, is becoming more common. This is especially important with the advent of the deployment of 5th generation (5G) networks which may offer the feature of fast device-to-device (D2D) communication. This dissertation proposes a method for optimal task offloading in H-MEC while jointly minimizing delay and energy consumption. Analysis on H-MEC task allocation with the joint time and energy minimization showed that the problem is NP-hard and hence, a heuristic solution was proposed. Results indicate that allowing one idle user to act as a server can provide up-to a 13% reduction in completion time and up-to 17% reduction in energy consumption. The focus of the dissertation then shifts to the major component of this work, which is enabling and optimizing the execution of machine learning tasks in a distributed manner, referred to as distributed Learning (DL), on H-MEC systems. Consequently, we design the novel paradigm of Mobile Edge Learning (MEL), where the goal is to allocate tasks optimally such that the ML model accuracy is maximized while taking into consideration the heterogeneous communication and computational capabilities of individual learners in a wireless MEC system. More specifically, our approach is heterogeneity aware (HA) compared to previous works which were heterogeneity unaware (HU). This part of the research investigates MEL optimal task allocation for synchronous (HA-Sync) and asynchronous (HA-Asyn) settings, with limits on the global completion time and local energy consumption. In the last part of the work, we provide recommendations on best scheme selection and how to apply the MEL in context of H-MEC. The problem of optimal task allocation in MEL is divided into four sub-problems consisting of HA-Sync and HA-Asyn with only time constraints and the HA-Sync/Asyn with dual time and energy constraints. All sub-problems are shown to be non-polynomial (NP) hard and hence, solutions based on relaxations are proposed. For the HA-Sync with time constraints, analytical upper bounds are proposed and shown to perform similar to the numerical approaches. For the HA-Asyn with time constraints and the HA-Sync/Asyn with dual time and energy constraints, solutions based on the suggest-and-improve (SAI) framework are proposed. Simulation results on MEL show that our proposed HA approaches achieve a superior validation accuracy and provide significant reductions in time for reaching a certain accuracy threshold compared to HU schemes when there is a limit on the global completion time. For example, the HA-Sync schemes reduce training time by up-to 25% compared to HU, whereas the HA-Asyn can provide further gains of up-to 10% in some settings. When there are joint global time and local energy consumption constraints, the HA-Sync/Asyn approaches can provide gains of up-to 25% compared to the HU schemes. Furthermore, because of different settings, where the HA-Asyn and HA-Sync outperform each other, this dissertation concludes by providing recommendations on how to select the appropriate scheme with the correct parameters, describing different application scenarios and identifying areas for future research.doctoral, Ph.D., Electrical and Computer Engineering -- University of Idaho - College of Graduate Studies, 2020-0
Deep Learning Approaches for Modeling and Inferring Neuronal Dynamics
No full textRecent developments in GPU-accelerated computing, as well as the advent of artificialintelligence and the rise of deep artificial neural networks (ANNs), have created a wealth of opportunity to explore purely data-driven computational modeling techniques on datasets and dynamical systems previously deemed overly complex or outright infeasible to model. One such example of a domain in which these questions are now being brought to light is in the field of computational neuroscience, where both single neuron and neuronal network dynamical responses prove difficult and arduous to model in many cases. This thesis work is dedicated to the development of computationally feasible, purely data-driven machine learning methods for inferring, learning, and modeling both single-neuron and many-neuron dynamics at multiple time-scales through novel employment of ANNs. The first portion of this dissertation focuses on the development of purely datadriven recurrent neural network (RNN) models of hippocampal CA1 pyramidal neuron dynamics in response to constant-amplitude applied external input. These CA1 pyramidal neurons exhibit highly nonlinear dynamics, with multiple bifurcations in behavioral response dependent on the magnitude of the externally applied input to the system. This approach involves the use of deep LSTM networks in conjunction with a novel translation trick borrowed from natural language processing (NLP) applications in language translation problems. We demonstrate that the network is capable of learning a complete representation of the dynamics, including multiple bifurcations in behavior. Additionally, we demonstrate that predictive accuracy of the devised LSTM network increases as the length of timeseries on which it is trained does as well. The second portion of this work focuses on the development of a generative machine learning method to infer firing rate dynamics of a neuronal population in an unsupervised autoencoding framework. This is centered around the idea that stochastic neuronal populations are better described using powerful rate-based dynamical models under the assumption that their firing activity can be described as a manyiv body nonhomogeneous Poisson point process. We use a sequential adaptation of a popular generative machine learning algorithm, the Variational Autoencoder (VAE) to infer firing rates that maximize the likelihood of the original data in an unsupervised manner, and demonstrate that this architecture is capable of discovering coherent dynamical representations of smoothed firing rates directly from binned spiking data.masters, M.S., Chemical and Materials Science Engineering -- University of Idaho - College of Graduate Studies, 2020-1
Single Crystal Deposition via Wire Arc Additive Manufacturing
No full textThe rapidly evolving field of additive manufacturing has developed from a niche manufacturing technique to a rapidly evolving manufacturing technique. The ability to manufacture complex geometries in addition to reduction in wasted materials common to subtractive manufacturing techniques has led to further inquiry not only in deposition methods but materials as well. One material that is currently manufactured at high expense are single crystal components. Single crystal components are typically subjected to harsh environments including high thermal exposure and repeated stress. The boundary-free lattice structure of a single crystal is ideal in these situations due to its high resistance to creep and fatigue crack growth. Current methods of manufacturing these components involve highly controlled directional solidification, a time and material costly procedure. The objective of this study is to investigate the feasibility of additively manufacturing single crystal components via Wire Arc Additive Manufacturing (WAAM) and with a variation of the Tungsten Inert Gas (TIG) process. WAAM tests were conducted using the University of Idaho’s WAAM machine, VandalForge, as well with the TIG variant. Material was deposited first onto an ultra-pure zone refined single crystal ingot for feasibility validation and then onto a 99.995% pure single crystal substrate oriented in the direction. Once deposits were made onto the substrates, samples were cold mounted in epoxy, polished and etched using Marble’s reagent. Optical Microscopy (OM) provided distinct images of segregated grain boundaries, however samples were also mapped with EBSD to confirm the effectiveness of the etchant for pure nickel grain boundaries. Further analysis of both OM and EBSD yielded that single crystal regions of deposited material had formed on the substrate.masters, M.S., Mechanical Engineering -- University of Idaho - College of Graduate Studies, 2020-1
Effects of Boulders on Bed Morphology and Hyporheic Flow
No full textStream hydromorphology regulates instream water flow and interstitial flow of water within streambed sediments, the latter known as hyporheic exchange. Whereas hyporheic flow has been studied in sand-bedded streams with ripples and dunes and in gravel-bedded streams with pool-riffle morphology, little is known about its characteristics in plane bed morphology with subdued streambed undulations and sparse macro-roughness elements such as boulders and cobbles. Here, we present a proof-of-concept investigation on the role of boulder-induced morphological changes on hyporheic flows based on coupling large-scale flume sediment transport experiments with computational fluid dynamics. Our results show that placement of boulders on plane beds increase the reach scale hyporheic median residence time, τ50, by 15% and downwelling flux, qd, by 18% from the plane bed. However, reach scale hyporheic exchange changes are stronger with τ50 decreasing by 20% and qd increasing by 79% once the streambed morphology reached equilibrium (with the imposed upstream sediment and flow inputs on boulders). These results suggest that hyporheic flow is sensitive to the geomorphic response from bed topography and sediment transport in gravel-bedded streams, a process that has been overlooked in previous work.masters, M.S., Water Resources -- University of Idaho - College of Graduate Studies, 2020-1
Artisanal Kefir: Antimicrobial Activity and Bacterial Populations
No full textFood products can be contaminated by a range of pathogenic and spoilage bacteria. Contamination of foods results in food spoilage and foodborne illnesses and leads to economic losses in the food industry. Similar to chemical antimicrobials, natural preservatives (biopreservatives) can be used to improve food quality and safety. Biologically-based preservation (biopreservation) uses lactic acid bacteria (LAB), their bacteriocins, bacteriophages and bacteriophage-encoded enzymes to ensure food safety and quality for foods that are not fermented. Among biopreservatives, bacteriocins are ribosomally synthesized small antimicrobial proteins, secreted by bacteria to inhibit the growth of other, usually closely related bacteria. Bacteriocins inhibit select pathogenic and/or spoilage bacteria without changing the chemical and physical characteristics of food. Kefir is a fermented dairy product made using kefir grains, which are composed of LAB and yeast in a protein-polysaccharide matrix called kefiran. Kefir has antimicrobial activity due to many metabolic products, including bacteriocins produced by LAB. For this study, it was hypothesized that international artisanal kefirs have diverse microflora, generating distinctive bacteriocin content, resulting in varied levels of antimicrobial activities. The objectives of this work were: 1) compare the antimicrobial activity of artisanal kefirs from Fusion Tea, Britain, the Caucuses region, Ireland, Lithuania, and South Korea against select foodborne pathogens, 2) examine whether the antimicrobial effect is due to bacteriocin production or other antimicrobials present in kefir, and 3) reveal bacterial populations and elucidate the diversity and abundance of LAB species in artisanal kefirs. This dissertation is comprised of two interconnected studies. In the first study, the antimicrobial activities of artisanal kefir products from Fusion Tea (A), Britain (B), Ireland (I), Lithuania (L), the Caucuses region (C), and South Korea (K) were investigated against select foodborne pathogens. Listeria monocytogenes CWD 1198, Salmonella enterica serovar Enteritidis ATCC 13076, Staphylococcus aureus ATCC 25923, and Bacillus cereus ATCC 14579 were inhibited by artisanal kefirs made with kefir grains from diverse origins. Kefirs A, B, and I inhibited all bacterial indicator strains examined at varying levels, except Escherichia coli ATCC 12435 (non-pathogenic, negative control). Kefirs K, L, and C inhibited all indicator strains, except S. aureus ATCC 25923 and E. coli ATCC 12435. Bacteriocins present in artisanal kefirs were determined to be the main antimicrobials in all kefirs examined. Kefir-based antimicrobials are being proposed as promising natural biopreservatives as per the results of the study. A typical kefir microbial community includes LAB, acetic acid bacteria, and yeast among other species in a symbiotic matrix. In the second study, the 16S rRNA gene sequencing was used to reveal bacterial populations and elucidate the diversity and abundance of LAB species in international artisanal kefirs from Fusion Tea, Britain, the Caucuses region, Ireland, Lithuania, and South Korea. Bacterial species found in high abundance in most artisanal kefirs included Lactobacillus kefiranofaciens, Lentilactobacillus kefiri, Lactobacillus ultunensis, Lactobacillus apis, Lactobacillus gigeriorum, Gluconobacter morbifer, Acetobacter orleanensis, Acetobacter pasteurianus, Acidocella aluminiidurans, and Lactobacillus helveticus. Some of these bacterial species are LAB that have been reported for their bacteriocin production capabilities and/or health promoting properties.doctoral, Ph.D., Food Science -- University of Idaho - College of Graduate Studies, 2020-1
Using Intelligent Anticipation to Improve Error-Prone Communication in Social Robots
No full textThis dissertation is centered on the study of anticipation behaviors based on Artificial Intelligence (AI) strategies as a method to improve the behavior of groups of autonomous ground robots by inferring the missing messages that get lost due to a noisy outdoor environment. These missing messages represent the information that the robots share as a group in order to stay synchronized. Also, this dissertation includes the study of an AI strategy as a method to recover corrupted phonetic messages. This research is inspired on the results of my Master thesis and expands on it to include more advanced anticipation techniques with a more complex navigation and sensors system for large environments; this research includes the use of GPS and compass for navigation and a (simulated) outdoor environment that is more realistic for many robotic applications and makes the inputs to the navigation system of the robot much noisier and more complex. This research also uses a small fleet of social robots whose collective behavior is less predictable and more complex. These issues make accurate communication between the robots a key and important feature and increase the need for anticipation as an aid to recover from faulty messages and events. A faulty event occurs when the communication between the robots gets interrupted and a message does not reach its destination. In addition, this work expands the study of anticipation from two robots (one leader and a follower) to larger groups of robots (one leader and multiple followers). In this case, the followers attempt to stay in formation while the group navigates between waypoints. This means that this group of robots must coordinate their navigation control with their formation control in a complex, simulated outdoor environment. The anticipation models presented in this research are based on Fuzzy Logic and Artificial Neural Networks models (ANN). The last one was trained using methods like Backpropagation and a Genetic Algorithm. We also designed the anticipation models based on two structures that are commonly used in System Identification Theory: AutoRegressive with eXogeneous input (ARX) and AutoRegressive Moving Average with eXogenous input (ARMAX). This research includes tests of how well anticipation works to improve coordination in complex environments. Also, we introduced an additional approach to message error correction based on syntax and phonetic inference as a complementary tool to message anticipation. This is based on the idea that some messages are not lost completely but their content can get corrupted. This approach uses an inference-based approach by implementing fuzzy logic theory in order to fully recover these corrupted messages. To test this idea, an approach based on human-robot interaction through voice commands was implemented. Here, external noise or even a user with a strong accent can confuse a speech engine and produce bad data. We define this as corrupted data and we use our solution to fix it. The results showed that the ARMAX models were more successful in reducing the distance error between both a pair of robots and a larger group of robots than the ARX models while the Leader Robot run missions included in the training data. On the other hand, the ARX models were more successful than the ARMAX models in developing a generalization behavior while the Leader Robot run missions that were not similar to the training data. Also, we observed that the ANN models that were trained with Genetic Algorithms had better results than the ANN models trained with Backpropagation. We also noticed that the robots were able to recover their formation from collisions that happened during their path. But they still can only take a certain amount of collisions before running out of time to reorganize themselves. In addition, the results from the speech experiments showed that our approach was successful in recovering corrupted messages created by a speech engine after generating homophone words in a voice command.doctoral, Ph.D., Computer Science -- University of Idaho - College of Graduate Studies, 2020-0