2018 MU theses - Access restricted to UM
Permanent URI for this collection
Browse
Recent Submissions
Item Indoor human activites recognition using audio signals based on support vector machines and convolutional neural networks(University of Missouri--Columbia, 2018) Zhang, Weican; He, Zhihai, 1973-[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI SYSTEM AT AUTHOR'S REQUEST.] Indoor human activities recognition can be of great importance in our daily life, especially for surveillance and security purposes, such as informing elderly people affected in hearing capabilities about environmental sounds (door bells, alarm signals, etc.). This thesis will present two approaches using audio signal processing: support vector machines method and convolutional neutral networks method. In both methods, audio feature extraction is needed since the original audio signal contains undesired information which could cause difficulties in audio recognition. For the support vector machines method, melfrequency cepstral coefficients are extracted from the original audio signals. With melfrequency cepstral coefficients, histogram feature can be generated using the concept of bag of words, which to be past into support vector machines algorithm, then the recognition results are generated by the algorithm. For convolutional neutral networks method, multiple audio features are extracted from the original audio signal including melfrequency cepstral coefficients, mel-scaled spectrogram, chroma feature and spectral contrast. These audio features are fed into a 5-layer convolutional neutral network, and the recognition results are generated by the network. The support vector machine method focusing on implementing the algorithm into a single chip machine, with a good accuracy at 90%. The convolutional neutral network method yields a much higher accuracy at around 97%.Item Vessels of humility(University of Missouri--Columbia, 2018) Pearson, Anthony; Clarke, Robert Bede[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI SYSTEM AT AUTHOR'S REQUEST.] My ceramic work is influenced by historical pottery and the vast barren Southwestern landscape. It consists of wheel thrown and hand formed pots such as jars, boxes and vases. These vessels become a vehicle for conversation and embody the essence of humility. I make work with a mindset of accepting the irregularities in the work. By roughly scraping the surfaces to create textures, I produce multiple irregularities, making the objects more relatable to the viewer. This work personifies and acknowledges humility and brings importance to the act of being. Through my making, I attempt to carry this modest feeling into my vessels. I am creating individual pieces to be viewed and experienced one by one. I choose to concentrate on using simple methods throughout my whole process. Through this aesthetic, I capture my vision and the humble tone I want to convey.Item Fuzzy-based conversational recommender for data-intensive science gateway applications(University of Missouri--Columbia, 2018) Ankathatti Chandrashekara, Arjun; Calyam, Prasad[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI SYSTEM AT AUTHOR'S REQUEST.] Neuro-scientists are increasingly relying on parallel and distributed computing resources for analysis and visualization of their neuron simulations. Although science gateways (SG) have democratized relevant high performance/throughput resources, users require expert knowledge and training to fully utilize the capabilities of a science gateway. In this thesis, we aim to investigate the socio-technical challenges and opportunities to use conversational agents that can be presented as chatbots in guided interfaces of next-generation SG.We explore a novel method to analyze user proficiency through a questionnaire design involving key cyberinfrastructure (CI)/SG stakeholders. Users interact with a context-aware chatbot that is embedded within SG to obtain simulation tools/resources to accomplish their goals. A questionnaire related to CI/SG and neuroscience domains is presented to the user and we use intuitionistic fuzzy logic to handle the fuzziness or vagueness in the user responses and create user profiles. We describe the use of a rule-based Mamdani Inference system which uses the user proficiency to provide guidance to users using an underlying recommender for cloud solution templates. The cloud solution template recommender suggests the best suitable cloud architecture to the users functional (RAM, CPU cores, storage) and nonfunctional (cost, performance, etc.) requirements. We explore the use of KNN algorithm to match user requirements with the catalog of templates to find most relevant templates based on user preferences. Evaluation results show that the questionnaire is consistent and reliable to capture the user proficiency in CI/SG and neuroscience domain. We simulate a series of queries from both expert and novice user and human expert annotation of the responses generated by the chatbot confirmed that our chatbot significantly helped in providing appropriate SG resources and tools based on user proficiency and thereby increasing the diffusion and adoption of CI/SG. We also show that our cloud solution recommender scheme improves the resource provisioning accuracy in a manufacturing science gateway application by up to 21% compared to the existing schemes.Item Cost-performance trade-offs in fog computing for IoT data processing of social virtual reality(University of Missouri--Columbia, 2018) Wang, Songjie; Calyam, Prasad[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI SYSTEM AT AUTHOR'S REQUEST.] Virtual Reality (VR)-based Learning Environments (VRLEs) are gaining popularity due to the wide availability of cloud and its edge (a.k.a. fog) technologies and high-speed networks. Thus, there is a need to investigate Internet-of-Things (IoT)-based application design concepts within social VRLEs to offer scalable, cost-efficient services that adapt to dynamic cloud/fog system conditions. In this thesis, we investigate the cost performance trade-offs for an IoT-based application that integrates large-scale sensor data from Social VRLEs and coordinates the real-time data processing and visualization across cloud/fog platforms. To facilitate dynamic performance adaptation of the IoT-based application with increased user scale, we present a set of cost-aware adaptive control rules. The implementation of the rules is based on an analytical queuing model that determines the performance states of the IoT-based application, given the current workload and the allocated cloud/fog resources. Using the IoT-based application in an exemplar VRLE use case, we evaluate the cost-performance trade-offs with three system architectures i.e., cloud-only, edge-only and edge-cloud architectures. Experiment results illustrate the best/worst practices in the cost-performance trade-offs for a range of simulated IoT scenarios involving monitoring user emotional data collected by using brain sensors. Our results also detail the impact of the system architecture selection, and the benefits in enabling feedback about student emotions to instructors during Social VR learning sessions. Lastly, we show the benefits of integrating our model-based feedback control in maximizing IoT-based application performance while keeping the associated costs at a minimum level.Item Porous silicates for applications in smart water treatment systems and antimicrobial biomedical coatings(University of Missouri--Columbia, 2018) Peixoto de Sousa, Caio; Hunt, Heather K.[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI SYSTEM AT AUTHOR'S REQUEST.] Porous silicates, particularly ordered ones, may find novel and wide-ranging applications in the bioengineering arena in the near future. For instance, zeolites, a family of microporous, crystalline aluminosilicates, are promising candidate materials for the fabrication of next-generation water treatment systems that not only remove unwanted pollutants from waste water, but also provide real-time quality monitoring of water quality. In a different field, drug-loaded, ordered mesoporous silicate coatings may provide improvements to the current standard of treating implant-borne bacterial infections. This thesis contains two studies aimed at advancing scientific knowledge towards making these applications feasible. First, as a first step toward "smart" or inherently-selective water treatment sensors and systems, we studied the fundamental spectroscopic properties of a commonly-used zeolite material; these properties provide the foundation for determining what types of sensor systems in which the materials could be used. Here, we report the investigation of the influence of three synthetic parameters (aging time, crystallization temperature, and crystallization time) on the infrared absorbance spectra of siliceous and aluminosilicate zeolite sodalite (SOD). We found that these parameters do not appear to interfere in SOD's absorbance modes. Rather, they seem to play a role in determining whether SOD will be formed, especially for its siliceous form. Furthermore, the experimental data reported here was used to validate Density Functional Theory models, which allow the interrogation of these materials properties with a higher degree of precision when compared to experimental analyses. This work demonstrates that these materials could potentially be applied as a selective coating to sensor surfaces without worrying that their synthetic parameters might alter the sensor's response. Secondly, as a first step towards using mesoporous silica materials as coatings for implantable devices, we studied the adsorption of the three most prevalent serum proteins: albumin, fibrinogen, and immunoglobulin G. We characterized these processes using bicinchoninic acid (BCA) assays. We investigated the influence of three parameters (initial protein concentration, incubation time, and calcination time) on the non-competitive adsorption of these model proteins onto mesoporous silica films employing a 3 x 3 Latin-square experimental design, performed in triplicate. Our results suggest that mesoporous silica has a higher affinity to albumin when compared to fibrinogen and immunoglobulin G. Moreover, we observed that proteins tend to adsorb in higher amounts with increasing concentration. Neither calcination time nor incubation time had significant effects on the adsorption process. These studies represent advances in our current understanding of the synthetic mechanisms of SOD and of the biocompatibility of mesoporous silica films. Further studies will be aimed at further elucidating SOD's potential to be used in high-tech water filtration systems and mesoporous silica coatings as potential materials for next-generation antimicrobial coatings.