Browsing Department of Computer Science and Engineering by Title
Now showing items 414-433 of 606
-
N-MODEL METHODOLOGY FOR ENHANCEMENT OF OBJECT-ORIENTED SOFTWARE
(2019-05-22)Software maintenance typically consumes an average of 60\% of software life costs, of which more than 60\% are spent on enhancements. These are a challenge for the software community, in which hundreds of millions of lines ... -
Neural Image and Video Understanding
(2017-08-25)Even though recent works on neural architectures have shown promising results at tasks like image recognition, object detection, playing Atari games, etc., learning a mapping from a visual space to a language space or vice ... -
Neural Network Architecture Optimization Using Reinforcement Learning
(2023-05-19)Deep learning has emerged as an increasingly valuable tool, employed across a myriad of applications. However, the intricacies of deep learning systems, stemming from their sensitivity to specific network architectures, ... -
A New Integrative Data Mining Framework For Analyzing The Cancer Genome Atlas Data
(Computer Science & Engineering, 2014-03-10)Besides accuracy and efficiency, understandability is another key issue of predictive modeling in real-world applications, especially in biomedical and healthcare data analysis. We develop a new integrative framework to ... -
New Matrix Completion Models For Social Information Retrieval Application
(Computer Science & Engineering, 2014-03-12)Many popular social web sites have emerged during the past decade and completely changed many users' everyday live. Recently, social information retrieval models, where conventional information retrieval meets the social ... -
Nonrigid Image Registration By The Deformation Based Grid Generation
(Computer Science & Engineering, 2009-09-16)A novel nonrigid image registration algorithm is developed using a well-established mathematic work known as deformation based grid generation. The deformation based grid generation is capable to generate a grid ... -
A Novel Architecture For Mobility Enabled Video Conferencing In Next Generation Wireless Networks
(Computer Science & Engineering, 2010-11-01)The Heterogeneous nature of next generation networks requires architecture and technologies that have an intrinsic support for diversity. The plethora of existing wireless access technologies will soon be connected to ... -
A Novel Game Theoretic Framework For Security In Wireless Sensor Networks
(Computer Science & Engineering, 2007-08-23)Due to severe resource limitations and often lack of centralized infrastructure, providing security in wireless sensor networks is a great challenge. Misbehavior due to malicious or faulty nodes can significantly degrade ... -
Novel Methods For Entity-centric Information Exploration
We witness an unprecedented proliferation of entity graphs that capture entities (e.g., persons, products, organizations) and their relationships. Such entity data gradually evolves into the most comprehensive knowledge ... -
A Novel Scheme For Contact Predictions In Opportunistic Networks
(Computer Science & Engineering, 2013-03-20)In the opportunistic network (ON) paradigm information is exchanged between two devices as they encounter each other. For such information exchange to take place the devices must know about the presence of other devices ... -
OGMA - LANGUAGE ACQUISITION SYSTEM USING IMMERSIVE VIRTUAL REALITY
(2016-05-10)One of the methods of learning a new language, or Second-Language Acquisition (SLA), is immersion, seen today as one of the most effective learning methods. Using this method, the learner relocates to a new place where the ... -
On Feasibility Of Fingerprinting Wireless Sensor Nodes Using Physical Properties
(Computer Science & Engineering, 2012-07-25)Fingerprinting wireless devices using physical properties has been recently suggested as an alternative for device identification and authentication. It has been found that the clock skew caused by the frequency discrepancy ... -
On the Efficacy of Knowledge Graph Completion Methods, Accuracy Measures and Evaluation Protocols
(2021-08-25)In the active research area of employing embedding models for knowledge graph completion, particularly for the task of link prediction, most prior studies used some specific benchmark datasets to evaluate such models. Most ... -
ON THE FEASIBILITY OF MALWARE UNPACKING WITH HARDWARE PERFORMANCE COUNTERS
(2019-05-08)Most of the malware authors use Packers, to compress an executable file and attach a stub, to the file containing the code, to decompress it at runtime, which will turn a known piece of malware into something new, that ... -
On The Influence of Spatio-Temporal Analysis on Clustering and Recommendation
(2017-12-04)In this dissertation, we propose efficient frameworks to analyze spatio-temporal data. In the first part of the dissertation, we use a clustering based method to mine useful information from trajectory data. Existing ... -
On-Line Environment Adaptation for User Performance Optimization
(2023-08-14)In today’s fast-paced and globally connected world, businesses are creating products with more significance to user personalization and customization. This has amplified the importance of capturing and learning user ... -
Online Efficient And Effective Search In Large And Noisy Sequence Databases
(Computer Science & Engineering, 2014-07-14)This thesis investigates the problem of similarity search in large and noisy sequence databases. A key application domain of interest in this work is the very challenging Query-By-Humming (QBH) problem, according to which, ... -
OPTIMAL UTILITY-BASED TRAFFIC CONTROL FOR DATACENTER NETWORKS
(2022-04-05)As datacenter applications with diverse service requirements proliferate, it becomes imperative to enable datacenter network flow rate allocation that satisfies minimum user-utility requirements, while allowing for ... -
Optimizing Resource Utilization, Efficiency and Scalability in Deep Learning Systems
(2023-05-01)This thesis addresses the challenges of utilization, efficiency, and scalability faced by deep learning systems, which are essential for high-performance training and serving of deep learning models. Deep learning systems ... -
OPTIMIZING THE DEMAND AND DISTRIBUTION OF POWER IN SMART GRIDS
(2021-08-16)The electricity is generated in bulk power plants and transported to the end-user through the transmission and distribution networks. The process incurs heavy losses adding to the operational costs. Secondly, fossil fuels ...