El presente trabajo toma como punto de inicio el crecimiento de la empresa ST S.A. Para los próximos cinco años ST S.A. se ha planteado importar mayor cantidad de maquinarias debido a la gran demanda en la compra de maquinarias que se ha experimentado en los últimos años en nuestro país; para ello tendrá que ampliar su línea de crédito con la matriz fábrica New Holland. Dos de los principales requerimientos de fábrica es de tener los EEFF de ST S.A. auditados por una firma internacional y que éstos sean emitidos mensualmente. Para poder cumplir con dicho requerimiento, STSA ha decidido optar por la implementación de un sistema ERP SAP Business One. Esta herramienta le permitirá principalmente a la empresa: Contar con información oportuna y segura, para emitir los EEFF y consultas de Stocks. Como consecuencia de este crecimiento, ST S.A. debe tomar decisiones importantes que le permitan mantener: - Mayor crecimiento del negocio y participación de mercado - Mejorar el enfoque de sus recursos en el CORE de su negocio - Contar con herramientas tecnológicas de costo accesible que le permitan mejorar su competitividad en el mercado y contar con información oportuna - Implementar plataformas de conectividad y comunicación en tiempo real las mismas que sirvan de ventaja competitiva a la empresa En tal sentido se ha considerado la presentación de la empresa ST S.A en un primer momento de crecimiento con sus recursos actuales, y la propuesta que el plan de tesis contempla es sustentar la implementación de un sistema ERP por medio de Cloud Computing, el mismo que de soporte a la mejora de transmisión de información; haciendo notar las ventajas competitivas y costos que serán logrados por ST S.A. El contar con un sistema alojado en Cloud Computing nos brindará mayor seguridad, respaldo de la información, eficiencia en costos y concentrarnos en el core del negocio.

This thesis presents a cloud platform for automatic speech recognition, CloudASR, built on top of Kaldi speech recognition toolkit. The platform sup- ports both batch and online speech recognition mode and it has an annotation interface for transcription of the submitted recordings. The key features of the platform are scalability, customizability and easy deployment. Benchmarks of the platform show that the platform achieves comparable performance with Google Speech API in terms of latency and it can achieve better accuracy on limited domains. Furthermore, the benchmarks show that the platform is able to handle more than 1000 parallel requests given enough computational resources. 1

Companies offering services on the Internet have led corporations to shift from the high cost of owning and maintaining stand-alone, privately-owned-and-operated infrastructure to a shared infrastructure model. These shared infrastructures are being offered by infrastructure service providers which have subscription, or pay-on-demand, charge models presenting compute and storage resources as a generalized utility. Utility based infrastructures that are run by service providers have been defined as "cloud computing" by the National Institute of Standards and Technology. In the cloud computing model the concerns of security and privacy protections are exacerbated due to the requirement for an enterprise to allow third parties to own and manage the infrastructure and be custodians of the enterprises information. With this new architectural model, there are new hybrid governance models designed to support complex and uncertain environments. The cloud also requires a common infrastructure that integrates originally separate computing silos. Privacy and security policy awareness during provisioning and computing orchestration about data locality across domains and jurisdictions must be able to obey legal and regulatory constraints. Commercial use of the Internet for electronic commerce has been growing at a phenomenal rate while consumer concern has also risen about the information gathered about them. Concern about privacy of data has been rated as the number one barrier by all industries. The purpose of this dissertation is to perform an empirical study to determine if existing privacy assessment instruments adequately assess privacy risks when applied to cloud infrastructures. The methodology for determining this is to apply a specific set of privacy risk assessments against a three cloud environments. The assessments are run in the context of a typical web based application deployed against cloud providers that have the five key cloud tenets - on-demand/self-service, broad network access, resource pooling, rapid elasticity, and measured service.

Data analysis of SYNOP observations was made for investigation of stratus formation in rain. The aim was to find connections between meteorological parameters in the different states of rain to develop a forecast method. 1594 cases of rainfall from the four stations Luleå, Uppsala, Linköping and Såtenäs, Sweden were analysed, 974 cases include stratus formation in rain and the other 620 cases are without stratus formation. The investigation focused on the meteorological parameters wind direction, wind speed, relative humidity, visibility, cloud base height and rain intensity. As rain intensity was not explicitly included in the SYNOP observations it could not be taken as a governing parameter, but classification of the data into four groups of different rain intensity was possible. Also time was a parameter for the investigation. The results show that a more detailed investigation should be made to eliminate several influences of other parameters, for example of radiation or soil conditions. Thus it was too difficult to develop a forecast method for the formation of stratus in rain, but suggestions for further investigations and the development of a numerical model only are made. / En dataanalys av SYNOP-observationer genomfördes för undersökning av stratusbildning i regn. Målet var att hitta samband mellan de meteorologiska parametrarna i olika regntillstånden för att utveckla en prognosmetod. 1594 regntillfällen från fyra stationer, Luleå, Uppsala, Linköping och Såtenäs, analyserades. 974 tillfällen innehåller stratusbildning i regn och de andra 620 tillfällena visar ingen stratusbildning. Undersökningen koncentrerades på de meteorologiska parametrarna vindriktning, vindhastighet, relativ fuktighet, sikt, molnhöjd och regnintensitet. Eftersom regnintensiteten inte var beskriven i SYNOP-observationer kunde den inte tas med som parameter i analysena. Det gick att indela datan i fyra grupper med olika regnintensitet. Tid var också en parameter i den här unders- ökningen. Resultater visar att det behövs en noggrannare undersökning för kunna eliminera påverkan av andra parametrar som till exempel strålning eller marktillstånd. Det var därför för svårt att utveckla en prognosmetod för stratusbildning i regn, så förslag har bara gjorts för vidare undersökningar och utveckling av en numerisk modell. / Für die Untersuchung der Stratusbildung im Regen wurde eine Analyse von SYNOP-Daten durchgeführt. Ziel war es, Zusammenhänge zwischen meteorologischen Parametern in den verschiedenen Stadien von Regen zu finden, um eine Vorhersagemethode zu entwickeln. Es wurden 1594 Regen- F¨alle von den Stationen Luleå, Uppsala, Linköping und Såtenäs in Schweden analysiert, von denen 974 Fälle Stratusbildung in Regen beinhalten. Die anderen 620 Fälle zeigen keine Stratusbildung. Die Untersuchung konzentrierte sich auf die meteorologischen Parameter Windrichtung, Windgeschwindigkeit, relative Feuchte, Sicht, Wolkenhöhe und Regenintensität. Da die Regenintensität nicht direkt in den SYNOP Beobachtungen gemessen wurde, konnte sie nicht als steuernder Parameter verwendet werden, sondern diente nur zur Einteilung der Daten in vier Gruppen verschiedener Regenintensität. Die Zeit ging als ein weiterer Parameter in diese Untersuchung ein. Die Ergebnisse zeigen, dass eine genauere Untersuchung durchgeführt werden sollte, um unterschiedliche Einflüsse anderer Parameter, wie zum Beispiel Strahlung oder Bodenbeschaffenheit, auszuschließen. Wegen der zu großen Unsicherheiten war es zu schwer, eine Prognosemethode f¨ur die Stratusbildung im Regen zu entwickeln. Deswegen wurden Vorschläge für weitere Untersuchungen und f¨ur die Entwicklung eines numerischen Modells gegeben.

Mobile Ad-hoc Cloud offers users the capability to offload intensive tasks on a cloud composed of voluntary mobile devices. Due to the availability of these devices in the proximity, intensive tasks can be processed locally. In addition, the literature referred to in the text, distinguishes a specific class of application to be well addressed when processed at the user level. However, due to lack of commitment, mobility, and unpredictability of the mobile devices, providing a rich ad-hoc cloud service is challenging. Furthermore, the resource availability of these devices impacts the service offered to the requester. As a result, this thesis aims to address the challenges mentioned above. With the support of Multi-Access Edge Computing, a mobile ad-hoc Infrastructure as a Service composition framework is proposed. An ad-hoc application server is designed to operate over the MEC platform to compose and manage the mobile ad-hoc cloud. The server uses the information provided by the MEC services to compose volunteer resources for a given request. As well, a heuristic approach for a multi-dimensional bin packing technique is considered, while extending the Euclidean distance for sub-tasks selection. In addition, to address the lack of resource availability, an architecture for MAC using SDN is proposed. The logically centralized controller works with the application server to migrate requests seamlessly from one region to another. Inspired by the benefits of the MEC, a mobility mechanism is introduced to address the movement of the participants. Finally, based on the evaluation, it was observed that the proposed MAC framework not only provided better use of resources but also provided a consisted and scalable service.

L'émergence de nouvelles plateformes décentralisées pour la création de données, tel que les plateformes mobiles, les capteurs et l'augmentation de la disponibilité d'open data sur le Web, s'ajoute à l'augmentation du nombre de sources de données disponibles et apporte des données massives sans précédent à être explorées. La notion de curation de données qui a émergé se réfère à la maintenance des collections de données, à la préparation et à l'intégration d'ensembles de données (data set), les combinant avec une plateforme analytique. La tâche de curation inclut l'extraction de métadonnées implicites et explicites ; faire la correspondance et l'enrichissement des métadonnées sémantiques afin d'améliorer la qualité des données. La prochaine génération de moteurs de gestion de données devrait promouvoir des techniques avec une nouvelle philosophie pour faire face au déluge des données. Ils devraient aider les utilisateurs à comprendre le contenue des collections de données et à apporter une direction pour explorer les données. Un scientifique peut explorer les collections de données pas à pas, puis s'arrêter quand le contenu et la qualité atteignent des niveaux satisfaisants. Notre travail adopte cette philosophie et la principale contribution est une approche de curation des données et un environnement d'exploration que nous avons appelé CURARE. CURARE est un système à base de services pour curer et explorer des données volumineuses sur les aspects variété et variabilité. CURARE implémente un modèle de collection de données, que nous proposons, visant représenter le contenu structurel des collections des données et les métadonnées statistiques. Le modèle de collection de données est organisé sous le concept de vue et celle-ci est une structure de données qui pourvoit une perspective agrégée du contenu des collections des données et de ses parutions (releases) associées. CURARE pourvoit des outils pour explorer (interroger) des métadonnées et pour extraire des vues en utilisant des méthodes analytiques. Exploiter les données massives requière un nombre considérable de décisions de la part de l'analyste des données pour trouver quelle est la meilleure façon pour stocker, partager et traiter les collections de données afin d'en obtenir le maximum de bénéfice et de connaissances à partir de ces données. Au lieu d'explorer manuellement les collections des données, CURARE fournit de outils intégrés à un environnement pour assister les analystes des données à trouver quelle est la meilleure collection qui peut être utilisée pour accomplir un objectif analytique donné. Nous avons implémenté CURARE et expliqué comment le déployer selon un modèle d'informatique dans les nuages (cloud computing) utilisant des services de science des donnés sur lesquels les services CURARE sont branchés. Nous avons conçu des expériences pour mesurer les coûts de la construction des vues à partir des ensembles des données du Grand Lyon et de Twitter, afin de pourvoir un aperçu de l'intérêt de notre approche et notre environnement de curation de données / The emergence of new platforms for decentralized data creation, such as sensor and mobile platforms and the increasing availability of open data on the Web, is adding to the increase in the number of data sources inside organizations and brings an unprecedented Big Data to be explored. The notion of data curation has emerged to refer to the maintenance of data collections and the preparation and integration of datasets, combining them to perform analytics. Curation tasks include extracting explicit and implicit meta-data; semantic metadata matching and enrichment to add quality to the data. Next generation data management engines should promote techniques with a new philosophy to cope with the deluge of data. They should aid the user in understanding the data collections’ content and provide guidance to explore data. A scientist can stepwise explore into data collections and stop when the content and quality reach a satisfaction point. Our work adopts this philosophy and the main contribution is a data collections’ curation approach and exploration environment named CURARE. CURARE is a service-based system for curating and exploring Big Data. CURARE implements a data collection model that we propose, used for representing their content in terms of structural and statistical meta-data organised under the concept of view. A view is a data structure that provides an aggregated perspective of the content of a data collection and its several associated releases. CURARE provides tools focused on computing and extracting views using data analytics methods and also functions for exploring (querying) meta-data. Exploiting Big Data requires a substantial number of decisions to be performed by data analysts to determine which is the best way to store, share and process data collections to get the maximum benefit and knowledge from them. Instead of manually exploring data collections, CURARE provides tools integrated in an environment for assisting data analysts determining which are the best collections that can be used for achieving an analytics objective. We implemented CURARE and explained how to deploy it on the cloud using data science services on top of which CURARE services are plugged. We have conducted experiments to measure the cost of computing views based on datasets of Grand Lyon and Twitter to provide insight about the interest of our data curation approach and environment

Os sistemas convectivos da região Amazônica possuem características microfísicas peculiares, que variam de um caráter convectivo marítimo (estação chuvosa) a continental (estação de transição seca-chuvosa). Essas características modulam a eletrificação desses sistemas, porém ainda não se sabe quais são os processos dominantes que intensificam o número de descargas elétricas de uma estação para outra: efeito dos aerossóis, termodinâmico, grande-escala ou topografia? Para responder à essa pergunta, o objetivo deste trabalho foi identificar e quantificar a importância de cada um desses efeitos na eletrificação dos sistemas convectivos da Amazônia. A metodologia foi baseada em análises de dados observacionais do experimento de campo DRYTOWET e em um modelo numérico com parametrizações de transferências de cargas e descargas elétricas. A análise do ciclo anual das descargas elétricas do tipo nuvem-solo (CGs) mostrou que a atividade elétrica dos sistemas precipitantes da região sudoeste da Amazônia aumenta durante a transição da estação seca para a estação chuvosa (Agosto a Setembro), associada aos sistemas convectivos com maior desenvolvimento vertical que acontecem nesse período. Com o estabelecimento da estação chuvosa (Novembro a Março), o número de CGs diminui porém a atividade elétrica ainda se mantêm. A porcentagem desses totais de CGs que tinham polaridade positiva (+CGs) tem média de 12% durante todo o ano, aumentando drasticamente para até 25% em Setembro, durante a transição entre as estações secas e chuvosa. Esse aumento da %+CGs ocorreu simultaneamente ao aumento da poluição atmosférica provocada pela queima de biomassa das pastagens realizada pelos fazendeiros locais, que as preparam para a agricultura e pecuária durante o início das primeiras chuvas. Por outro lado, o aumento da %+CGs das tempestades também ocorreu preferencialmente sobre a área de pastagem do estado de Rondônia. Através da análise de dados de radar dos sistemas precipitantes que ocorreram durante o experimento DRYTOWET, foi constatado que as tempestades positivas (tempestades que produzem mais de 50% de +CGs em 50% de seu tempo de vida) se formaram em ambientes mais secos e com alturas do nível de convecção por levantamento (NCL, altura da base da nuvem) maiores do que as demais tempestades (tempestades negativas), durante todo o experimento mas com maiores diferenças durante o final da estação seca (Setembro-Outubro). Com altura da base da nuvem mais elevada, a espessura da camada quente (ECQ - base da nuvem até a isoterma de 0oC) diminui, aumentando assim a velocidade das correntes ascendentes através de um melhor processamento da energia potencial disponível para convecção (CAPE) devido a um menor entranhamento. O aumento da velocidade das correntes ascendentes dentro da nuvem resulta em tempestades mais profundas e mais intensas. O efeito do aumento do NCL é uma característica das regiões com vegetação de pastagem, onde a razão entre o calor sensível e latente na superfície é maior do que as áreas florestadas, aumentando a altura da camada limite planetária. As diferenças de concentração total e distribuição de tamanho dos aerossóis devido ao aumento da poluição durante a transição entre as estações seca e chuvosa não foram conclusivas quanto a um possível efeito na distribuição de hidrometeoros das tempestade positivas e negativas, uma vez que o ciclo diurno da concentração dos aerossóis acompanha o ciclo diurno da camada limite planetária, que também regula o efeito da ECQ. Simulações numéricas com um modelo 1D de nuvem, acoplado à parametrizações de transferências de cargas elétricas entre hidrometeoros e raios, mostraram que a estrutura termodinâmica da atmosfera foi a maior responsável pela eletrificação das tempestades simuladas, aumentando a velocidade das correntes ascendentes. O efeito do aumento do número de aerossóis, que inibe da fase quente da nuvem e conseqüentemente fortalece a da fase fria da nuvem fornecendo mais vapor e gotículas de nuvem para essa região, provocou a diminuição da quantidade de granizo nas tempestades simuladas e o aumento de partículas agregadas menores, como os flocos de neve e graupel, diminuindo a freqüência de raios. / Amazonian convective systems have unique microphysical characteristics, varying from a maritime convective behavior (rainy season) to a continental behavior (wet-dry transition season). These characteristics modulate the electrification of these systems, however it is still not well understood which are the dominant processes that intensify the frequency of lightning from one season to another: aerosol effect, thermodynamics, large-scale variability, landscape or topography? To answer this question, the objective of this study was to identify and quantify the importance of each one of these effects on the electrification of convective systems over the Amazon. The methodology was based on the analysis of observational data from the field experiment DRYTOWET and a numerical model with charge transfer parameterizations and lightning discharges. The cloud-to-ground (CG) lightning discharges annual cycle presented that the electrical activity of the southwestern Amazonian precipitating systems increased during the transition between the dry and wet seasons (August to September), in association with the convective systems deepening. With the establishment of the wet season (November to March), the number of CGs decreased but the electrical activity continued. The mean annual percentage of cloud-to-ground lightning of positive polarity (+CGs) was 12%, increasing drastically to 25% in September during the transition between the dry and wet seasons. This percentage of +CGs raise happened simultaneously with the increase in the atmospheric pollution due to the pasture biomass burning, held by local farmers to prepare the soil for agriculture and livestock during the begging of first rains. On the other hand, the increase in %+CGs also occurred preferentially over pasture areas of Rondonia state. Through the analysis of radar precipitating systems that occurred during the field campaign DRYTOWET, it was noted that positive thunderstorms (storms that produced more than 50% of +CGs over 50% of their life time) were initiated in drier and higher lift condensation levels (cloud base height) environments than other storms (negative thunderstorms) during all the field experiment, especially in the end of the dry season (September-October). A higher cloud base height is associated with a shallower warm cloud depth (cloud base height to the 0oC isotherm) and consequently less entrainment, increasing the updrafts due to a more efficient processing of the convective available potential energy (CAPE). This increase in updrafts inside the clouds results in deeper and stronger thunderstorms. The higher cloud base heights is a characteristic from pasture regions, where the ratio between sensible and latent heats at surface is greater than forested areas, which increases the top of the planetary boundary layer. The differences in the aerosol total concentration and size distribution, due to the increase in the atmospheric pollution during the transition between the dry and wet seasons, were inconclusive in a possible aerosol effect in the strength of positive and negative thunderstorms, once the aerosol concentration diurnal cycle follows the cycle of the planetary boundary layer, that also regulates the warm cloud depth effect. Numerical simulation of an 1D cloud model, coupled with charge transfer between the hydrometeors, showed that the thermodynamic structure was the main responsible feature for cloud electrification, increasing the updraft velocities. The pollution effect was masked in simulations, which inhibit the warm precipitation and consequently strength the the mixed and cold regions of the cloud, was responsible for an increase in the number of smaller aggregated particles, like snow flakes and graupel, decreasing the electrification and lightning frequency.

<div>Latency is regarded as the Achilles heel of cloud computing. Pricing is an essential component in the cloud market since it not only directly affects a cloud service provider's (CSP's) revenue but also a user's budget. This dissertation investigates the latency-aware pricing schemes that provide rigorous performance guarantees for the cloud market. The research is conducted along the following major problems as summarized below:</div><div><br></div><div>First, we will address a major challenge confronting the CSPs utilizing a tiered storage (with cold storage and hot storage) architecture - how to maximize their overall profit over a variety of storage tiers that offer distinct characteristics, as well as file placement and access request scheduling policies. To this end, we propose a scheme where the CSP offers a two-stage auction process for (a) requesting storage capacity, and (b) requesting accesses with latency requirements. Our two-stage bidding scheme provides a hybrid storage and access optimization framework with the objective of maximizing the CSP's total net profit over four dimensions: file acceptance decision, placement of accepted files, file access decision and access request scheduling policy. The proposed optimization is a mixed-integer nonlinear program that is hard to solve. We propose an efficient heuristic to relax the integer optimization and to solve the resulting nonlinear stochastic programs. The algorithm is evaluated under different scenarios and with different storage system parameters, and insightful numerical results are reported by comparing the proposed approach with other profit-maximization models. We see a profit increase of over 60% of our proposed method compared to other schemes in certain simulation scenarios.</div><div><br></div><div>Second, we will resolve one of the challenges when using Amazon Web Services (AWS). Amazon Elastic Compute Cloud (EC2) provides two most popular pricing schemes--i) the costly on-demand instance where the job is guaranteed to be completed, and ii) the cheap spot instance where a job may be interrupted. We consider a user can select a combination of on-demand and spot instances to finish a task. Thus he needs to find the optimal bidding price for the spot-instance, and the portion of the job to be run on the on-demand instance. We formulate the problem as an optimization problem and seek to find the optimal solution. We consider three bidding strategies: one-time requests with expected guarantee, one-time requests with penalty for incomplete job and violating the deadline, and persistent requests. Even without a penalty on incomplete jobs, the optimization problem turns out to be non-convex. Nevertheless, we show that the portion of the job to be run on the on-demand instance is at most half. If the job has a higher execution time or smaller deadline, the bidding price is higher and vice versa. Additionally, the user never selects the on-demand instance if the execution time is smaller than the deadline. The numerical results illustrate the sensitivity of the effective portfolio to several of the parameters involved in the model. Our empirical analysis on the Amazon EC2 data shows that our strategies can be employed on the real instances, where the expected total cost of the proposed scheme decreases over 45% compared to the baseline strategy.<br></div>

This thesis is composed of three main parts. Each chapter is concerned with characterizing some properties of a random ensemble or stochastic process. The properties of interest and the methods for investigating them di er between chapters. We begin by establishing some asymptotic results regarding zeros of random harmonic mappings, a topic of much interest to mathematicians and astrophysicists alike. We introduce a new model of harmonic polynomials based on the so-called "Weyl ensemble" of random analytic polynomials. Building on the work of Li and Wei [28] we obtain precise asymptotics for the average number of zeros of this model. The primary tools used in this section are the famous Kac-Rice formula as well as classical methods in the asymptotic analysis of integrals such as the Laplace method. Continuing, we characterize several topological properties of this model of harmonic polynomials. In chapter 3 we obtain experimental results concerning the number of connected components of the orientation-reversing region as well as the geometry of the distribution of zeros. The tools used in this section are primarily Monte Carlo estimation and topological data analysis (persistent homology). Simulations in this section are performed within MATLAB with the help of a computational homology software known as Perseus. While the results in this chapter are empirical rather than formal proofs, they lead to several enticing conjectures and open problems. Finally, in chapter 4 we address an industry problem in applied mathematics and machine learning. The analysis in this chapter implements similar techniques to those used in chapter 3. We analyze data obtained by observing CAN tra c. CAN (or Control Area Network) is a network for allowing micro-controllers inside of vehicles to communicate with each other. We propose and demonstrate the e ectiveness of an algorithm for detecting malicious tra c using an approach that discovers and exploits the natural geometry of the CAN surface and its relationship to random walk Markov chains. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2018. / FAU Electronic Theses and Dissertations Collection

Dracula orchids are hypothesized to rely on mushroom mimicry for pollination. These orchids look and smell like mushrooms and are pollinated by mushroom-associated flies in the family Drosophilidae. Dracula includes over 130 species, representing a significant radiation, yet there has never been a systematic study of their pollination biology. Elucidating the processes and mechanisms of pollination in these flowers will broaden our understanding of mimicry within the Orchidaceae, a family well known for its diverse pollination strategies, as well as add to the growing literature on the evolution and maintenance of communication signals. In this study we demonstrate the co-occurrence of the mimics and the putative mushroom models, which is important for evolution by natural selection. We also showed that the resemblance to mushrooms is in fact adaptive, a requisite for floral mimicry. We did this by determining that insect visitors are required for pollination and subsequent fruit set with a hand pollination experiment. We also measured increased visitation rates to the orchids when adjacent to mushrooms. The mechanisms whereby plants attract pollinators can be diverse and often multi-modal, particularly in deceptive systems. Dracula orchids are no exception, with both visual and olfactory signals contributing to the overall success in attracting visitors. We used a series of experiments, first selectively masking the visual and olfactory cues successively, and then using 3D-printed artificial flowers to further disentangle these cues and determine their effect in combination. Upon confirmation that both play a role, we dissected each aspect further. We utilized the artificial flowers to determine the roles of color, contrast, and pattern and employed gas chromatography-mass spectroscopy to identify the volatile signals. The results show that fine-scale contrast is critical to the visual component and that these flowers produce the volatile `mushroom-alcohol' (1-octen-3-ol) in their labella. Finally, we specifically address the hypothesis of brood-site mimicry by using a combination of field observations, insect collections, and rearing studies. The flies gain shelter, a rendezvous location, and food from the flowers. However, no mushroom visiting flies hatched from the flowers, suggesting this may be a brood-site mimicry. This dissertation includes previously unpublished co-authored material. / 2015-09-29