Search
Now showing items 1-20 of 117
Achieving Optimal Schedule by Network Flow Techniques
(2015-08-11)
Scheduling plays an important role in protocol design and performance optimizations for
wireless or wired networks. This dissertation studies how to achieve optimal performance
for two fundamental scheduling problems ...
An Energy Efficient Addressing Scheme For a Static Wireless Sensor Network
(University of Missouri--Kansas City, 2011-01-20)
extensible. We also present simulation results showing the energy required per packet transmission and overhead analysis in our approach is less as compared to other work. This thesis starts with an introduction to Wireless Sensor Networks and the Directional...
Integration Features in the Development of Software Product Line Architecture
(2015-08-12)
Software product line architecture (PLA) is one of the most promising applications of software architecture. This paper presents a pragmatic PLA development approach with tool support. It addresses two existing issues of PLA development...
Network partition for switched industrial ethernet using combined search heuristics
(University of Missouri--Kansas City, 2011-06-06)
by the previous one, and both papers used genetic algorithms. This thesis investigated the NPP problem and concluded by extensive tests that it is very difficult to improve further if we purely follow the method of genetic algorithms. Motivated by searching...
KB4DL: Building a Knowledge Base for Deep Learning
(University of Missouri -- Kansas City, 2019)
Deep Learning (DL) has received considerable attention from the AI community. However, we
suffer from the lack of ability in interpretation and annotation of the outcomes from
extensive and exhausting learning efforts. ...
Maintaining Conformance Between Product Line Architecture and Source Code in Architecture-Centric Product Line Development
(2016)
Automatically maintaining conformance between product line architecture and source
code is a major challenge involved in architecture-centric product line development. This is
difficult as existing techniques of ...
NCC-EM: A hybrid framework for decision making with missing information
(University of Missouri--Kansas City, 2017)
Accounting for uncertainty is important in any data driven decision making. The
popular treatment of uncertainties is to employ classical probability theory by expressing
variables as random variables or processes in ...
Siamese Network-Based Multi-Modal Deepfake Detection
(2020)
Deep learning widely applies to solve various problems in healthcare, robotics, and computer vision. Presently, an emerging deep learning application called "deepfake" has raised concerns about the multiple types of security threats that may pose...
Ocular motion classification for mobile device presentation attack detection
(2020)
sophisticated, ocular motion based presentation attack detection (PAD) methods provide a potential deterrent. This dissertation presents the methods and evaluation of a novel optokinetic nystagmus (OKN) based PAD system for mobile device applications which...
Building a reliable and secure management framework for software-defined networks
(2021)
controller. Extensive Mininet experimental results validate that the framework significantly improves discovery message efficiency and makes the control traffic less bursty than OFDP with a uniform timer. It also reduces the network status discovery delay...
Implementing Product Line Architecture with Code Generation and Separation
(University of Missouri--Kansas City, 2016)
Software product line engineering (SPLE) emphasizes high level of reuse and mass
customization of the core assets shared by a family of software products. Product line
architecture (PLA) is a promising application of ...
SigsSpace-Text: Parallel and Distributed Signature Learning in Text Analytics
(University of Missouri--Kansas City, 2016)
extension, the proposed SigSpace-Text approach brings vital, practical information to signature learning approaches on several text classification tasks. The SigSpace-Text model supports incremental, distributed, and parallel learning using big data...
MDRED: Multi-Modal Multi-Task Distributed Recognition for Event Detection
(University of Missouri -- Kansas City, 2018)
Understanding users’ context is essential in emerging mobile sensing applications, such
as Metal Detector, Glint Finder, Facefirst. Over the last decade, Machine Learning (ML)
techniques have evolved dramatically for ...
Topic network: a semantic model for effective learning
(University of Missouri--Kansas City, 2011-06-08)
There has been tremendous interest in sharing and retrieving information through the Web. A
search engine can be used to retrieve relevant web documents. However, the sheer volume of
results returned often requires ...
Energy Efficient Resource Allocation for Virtual Network Services with Dynamic Workload in Cloud Data Centers
(2015)
With the rapid proliferation of cloud computing, more and more network services and
applications are deployed on cloud data centers. Their energy consumption and green
house gas emissions have significantly increased. ...
Volatility-Aware Query Processing in Peer-to-Peer Systems
(University of Missouri--Kansas City, 2010)
with highly transient populations of peers, and the dynamicity of P2P systems. CDQP assumes peers participating in a query plan are always present during query execution. Furthermore, it uses the compile-then-execute approach whose effectiveness relies heavily...
Video Streaming Quality of Experience (QoE): In-network Cache Prefetching and Moving QoE Models
(2021)
environment. We compared our models with an extension of the Model Predictive Control (MPC) QoE model (referred to as MQoE_MO). Our study shows the robustness of our MQoE models. The results show how the MQoE models is able to more accurately capture...
AudioCNN: Audio Event Classification With Deep Learning Based Multi-Channel Fusion Networks
(2020)
techniques. We have conducted our extensive experiments with benchmark datasets, including Urbansound8k, ESC-50, and ESC-10, emotion datasets. We have obtained state-of-the-art results by outperforming the previous solutions. The experiment results show...
A Hardware/Software Co-integration Approach for Securing Network Infrastructure using Reconfigurable Computing
(2022)
with circuit size and topology. Compared to other popular MVL decomposition methods, the proposed algorithm presents significant savings in hardware overhead and computational complexity. In recent years, small but significant research efforts have been...
Distributed Perimeter Firewall Policy Management Framework
(University of Missouri--Kansas City, 2017)
A perimeter firewall is the first line of defense that stops unwanted packets (based on
defined firewall policies) entering the organization that deploys it. In the real world, every
organization maintains a perimeter ...