RSS 1.0Theses and Dissertations-Computer Science
Browse by
Recent Submissions
-
Energy efficiency analysis and optimization of relational and NoSQL databases
(2016-11-28)As big data becomes the norm of various industrial applications, the complexity of database workloads and database system design has increased significantly. To address these challenges, conventional relational databases ... -
Defragmenting Social Networks
(2017-11-20)The scale of Online Social Networks, like Facebook, requires splitting users across many servers; unfortunately, this can spread one user's friends across hundreds of servers, increasing both the latency of retrieving all ... -
Combining Deep Learning with Traditional Machine Learning to Improve Classification Accuracy on Small Datasets
(2017-11-30)Feature extraction and selection are essential phases in building machine learning classification models, and they have a great impact on the accuracy and the performance of the model. However, these phases are expensive, ... -
Using the Greenup, Powerup And Speedup Metrics To Evaluate Software Energy Efficiency
(2016-07-21)Green computing has made significant progress in the past decades, which is evidenced by more energy efficient hardware (e.g. low power CPUs, GPUs, SSDs) and better power management and cooling techniques at data centers. ... -
Energy Efficiency Analysis and Optimization of Convolutional Neural Networks For Image Recognition
(2016-04-26)In recent years, convolutional neural network (CNN) has been widely used to improve the training time and accuracy of image recognition applications. These CNNs are based on deep learning algorithms, which simulate the ... -
Implementation and evaluation of an android accessor-based IoT middleware
(2017-07-26)This thesis proposes an IoT middleware for Android using V8 script engine. This middleware supports the accessor abstraction for IoT and composes IoT applications based on various accessors implemented in JavaScript. ... -
Friend circle and social feature-based routing in opportunistic mobile social networks
(2017-07-25)Opportunistic Mobile Social Networks (OMSNs), formed by people moving around carrying mobile devices, enhance spontaneous communication among users that opportunistically encounter each other without additional infrastructure. ... -
Object Recognition using Moments of the Signature Histogram
(2017-04-25)The amount of digital information generated each day is increasing at a very high rate. Our ability to understand and make sense of such large amounts of unstructured data depends on efficient and reliable methods to ... -
-
An Efficient Connected Components Algorithm for Massively-Parallel Devices
(2017-04-07)Massively-parallel devices such as GPUs are best suited for accelerating regular algorithms. Since the memory access patterns and control flow of irregular algorithms are data dependent, such programs are more difficult ... -
HASTE: A Heterogeneously Accelerated SQL Transaction Engine
(2014-11-21)Databases are the backbone of the digital age and empower the storage and processing of massive amounts of data. As private and public data grows at an astonishing rate, the technologies that drive data processing must ... -
Determination of Emotional State through Physiological Measurement
(2016-11-28)The goal of this thesis is to develop and evaluate methods of emotional response classification using human physiological data. With the continued development of automated systems that interact closely with humans in a ... -
Analysis of human polysomnography (PSG) for automatic sleep event detection using Hidden Markov Model
(2016-07-27)This thesis work evaluates our proposed methodology for automated detection of sleep events from Polysomnographic (PSG) data. The sleep data was collected during real sleep studies using Profusion PSG3. The event detection ... -
The Effect of Decoy Attacks on Dynamic Channel Assignment
(2014-11-18)As networks grow rapidly denser with the introduction of wireless-enabled cars, wearables and appliances, signal interference coupled with limited radio spectrum availability emerges as a significant hindrance to network ... -
Towards a Framework for Automating the Workflow for Building Machine Learning Based Performance Tuning
(2016-07-27)Recent interest in machine learning-based methods have produced many sophisticated models for performance modeling and optimi:,ation. These models tend to be sensitive to architectural parameters and are most effective ... -
Improving Bandwidth Allocation in Cloud Computing Environments via "Bandwidth as a Service" Partitioning Scheme
(2016-07-19)Cloud computing is a relatively new idea where virtualized computers commu- nicating with each other perform a multitude of services such as general purpose computing, cloud services to local applications for storage or ... -
Recommender response to user profile diversity and popularity bias
(2016-07-19)Recommender systems are commonly evaluated to understand the effectiveness of their algorithms. Diversity and novelty of the recommender systems have been in consideration while evaluating the systems in addition to accuracy ... -
Exploring Potentially Discriminatory Biases In Book Recommendation
(2016-07-20)Recent issues which occurred in the field of artificial intelligence present disproportionality based on protected attributes such as sex, race, and ethnicity in their output had raised concerns. The algorithms used in AI ... -
Improving Top-N Evaluation of Recommender Systems
(2016-07-19)Recommender systems are used to provide the user with a list of recommended items to help user find new items they might prefer. One of the main task of the recommender is to provide such items that the user has not seen ... -
Learning Image Saliency from Human Touch Behaviors
(2013-07-16)The concept of touch saliency has recently been introduced as a possible alternative for eye tracking in usability studies. This touch saliency study shows that image saliency maps can be generated based on human simple ...
