Search
Now showing items 41-60 of 123
ClaimChain: secure Blockchain platform for handling insurance claims processing
(University of Missouri--Columbia, 2021)
-level fraud modeling for identified prominent red flags through machine learning models and risk scoring on the basis of risk severity. The scalability of ClaimChain is evaluated by simulating realistically large number of Blockchain transactions of claim...
Design and implementation of a portable prTorrent simulator system
(University of Missouri--Columbia, 2010)
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] The absence of a system that could perform as both a P2P simulator and a P2P emulator poses a barrier to researchers and developers. The objective of ...
Deep learning for small object detection in images
(University of Missouri--Columbia, 2020)
algorithm, called GODM, to take the spatial information of candidate objects into consideration in small object detection. Instead of detecting small objects independently as the existing deep learning methods do, GODM treats the candidate bounding boxes...
Deep learning architectures for 2D and 3D scene perception
(University of Missouri--Columbia, 2021)
- Grad operator with graph convolution on scattered irregular point sets captures the salient structural information in the point cloud across spatial and feature scale space, enabling efficient learning. We integrated PointGrad with several deep network...
Intelligent orchestration of computation and networking for drone swarm applications
(University of Missouri--Columbia, 2023)
the development of drone-network testbeds in terms of trace-based, learning-based, and scientific workflow supported. In addition to this, the application use cases on how drone swarms can benefit in various scenarios, i.e., disaster management, last-mile parcel...
New methods for protein structure prediction using machine learning and deep learning
(University of Missouri--Columbia, 2022)
machine learning and deep learning methods have been proposed for protein model quality assessment, protein contact prediction, protein model refinement, and loop modeling. The goal of model quality assessment (QA) is to estimate the quality of predicted...
Exploring deep learning techniques to tackle the sparsity problem in recommender systems
(University of Missouri--Columbia, 2020)
interactions, attracting new customers, and growing business revenue. Machine learning, and deep learning (DL) in particular, have achieved a great success in resolving various computer science problems. Generally, DL-based approaches have enhanced performance...
Mining progressive user behavior for e-commerce using virtual reality technique
(University of Missouri--Columbia, 2007)
behavior through VR tools, and 3) vast amount of information to mine and efficient summarization of the results to guide user's navigation. To overcome these obstacles, several techniques from the fields of Information Retrieval and Data Mining & Knowledge...
Pathway curator: an online webserver extracting genes and interactions from figures
(University of Missouri--Columbia, 2022)
increase of the literature requires laborious extraction of information from a publication at a time. A gene pathway map recognition system is devised and implemented in this study. Based on the pathway map and relevant information supplied by users...
Local and deep texture features for classification of natural and biomedical images
(University of Missouri--Columbia, 2019)
Developing efficient feature descriptors is very important in many computer vision applications including biomedical image analysis. In the past two decades and before the popularity of deep learning approaches in image classification, texture...
Deep learning methods for 360 monocular depth estimation and point cloud semantic segmentation
(University of Missouri--Columbia, 2022)
geometry-aware feature fusion mechanism that combines 3D geometric features with 2D image features. (ii) the self-attention-based transformer architecture to conduct a global aggregation of patch-wise information. (iii) an iterative depth refinement...
Decoder-learning based distributed source coding for high-efficiency, low-cost and secure multimedia communications
(University of Missouri--Columbia, 2008)
statistics is assumed. For DSC of real-world sources such as images and videos, such knowledge is not really available. In this dissertation, we focus on designing decoder-side learning schemes for better understanding of the source statistics, based on which...
Detecting targeted data poisoning attacks on deep neural networks
(University of Missouri--Columbia, 2022)
the DNN to learn malicious behavior. In the context of facial authentication, this could correspond to unauthorized users gaining access to a target's account, whereas, in deepfake detection, this could translate to causing the DNN to fail to identify when...
Development of web services in academic environment
(University of Missouri--Columbia, 2019)
tool to help us spread information and help companies to perform product promotion. Nowadays, web services are also a new tool in modern life to help people make work easier and live better. Website development is a growing aspect of Information...
Improving protein structure prediction by deep learning and computational optimization
(University of Missouri--Columbia, 2019)
, and fourth, multi-domain assembly. In recent years, deep learning techniques have proved to be a highly effective machine learning method, which has brought revolutionary advances in computer vision, speech recognition and bioinformatics. In this dissertation...
Statistical optimization of acoustic models for large vocabulary speech recognition
(University of Missouri--Columbia, 2006)
and the HMM gradient boosting algorithm. Investigations are conducted to applying both methods to improve word error rate of the state-of-the-art speech recognition system. However, these two methods are developed in a general machine learning background...
Selecting data for multilingual multi-domain neural machine translation on low resource languages
(University of Missouri--Columbia, 2020)
requires a quantitative synthesis of all these factors. We evaluate a number of techniques to measure each of these factors and learn a system combining them. The focus is on the Luyia languages of western Kenya as a case study for an extreme low resource...
Building environmentally-aware classifiers on streaming data
(University of Missouri--Columbia, 2022)
in creating algorithms that continually learn during inference. An unsupervised streaming approach addresses all three of these challenges, storing only a finite amount of information to model an unbounded dataset and adapting to new structures as they arise...
Dashboard design and usability study for geospatially enabled information seeking to assist pandemic response and resilience
(University of Missouri--Columbia, 2021)
Counties in Missouri are primarily rural. Rural communities often consist of individuals with poor health, lower economic status, and lack of public health infrastructure. During the COVID- 19 pandemic, most research was centered around urban...
Intelligent user interfaces for internet-of-things based web applications
(University of Missouri--Columbia, 2016)
Internet-of-Things technologies. A variety of smart devices over cloud/fog edge networks can generate huge amounts of data that has to be collected, analyzed in real-time to gain actionable insights. A good example of such needs can be seen in verticals...